⚡
Performance benchmark
How fast is the model?
Raw throughput on real hardware – how many tokens a model generates per second, how quickly it processes the prompt and how short the time to first token is. Higher is better.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 561,43 tok/s TG Prefill 27.407 · TTFT 973 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 2 | Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 492,68 tok/s TG Prefill 18.535 · TTFT 1.471 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 3 | Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 449,35 tok/s TG Prefill 21.718 · TTFT 571 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 4 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 427,76 tok/s TG Prefill 8.456 · TTFT 2.403 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 5 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,16 tok/s TG Prefill 14.911 · TTFT 2.001 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 6 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 364,13 tok/s TG Prefill 15.658 · TTFT 1.918 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 7 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 361,84 tok/s TG Prefill 7.233 · TTFT 2.750 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 8 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 353,85 tok/s TG Prefill 4.758 · TTFT 4.353 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 344,85 tok/s TG Prefill 4.759 · TTFT 5.325 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 10 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 325,24 tok/s TG Prefill 9.520 · TTFT 2.933 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 11 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 323,59 tok/s TG Prefill 5.090 · TTFT 3.955 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 12 | Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 320,89 tok/s TG Prefill 13.760 · TTFT 902 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 13 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 295,16 tok/s TG Prefill 4.265 · TTFT 6.027 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 14 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 294,37 tok/s TG Prefill 4.193 · TTFT 6.057 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 15 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 289,42 tok/s TG Prefill 10.849 · TTFT 1.212 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 16 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 288,80 tok/s TG Prefill 4.736 · TTFT 6.808 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 17 | Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 283,50 tok/s TG Prefill 4.190 · TTFT 6.068 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 18 | gemma-3n-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 277,51 tok/s TG Prefill 4.348 · TTFT 4.623 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 19 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 275,62 tok/s TG Prefill 6.734 · TTFT 1.481 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 20 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 275,30 tok/s TG Prefill 4.383 · TTFT 5.205 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 21 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,22 tok/s TG Prefill 7.074 · TTFT 1.399 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 22 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 261,48 tok/s TG Prefill 13.512 · TTFT 1.061 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 23 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,77 tok/s TG Prefill 9.631 · TTFT 3.487 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 24 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 255,41 tok/s TG Prefill 6.332 · TTFT 1.575 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 250,57 tok/s TG Prefill 9.085 · TTFT 3.442 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 26 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 250,18 tok/s TG Prefill 7.760 · TTFT 4.096 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 27 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 248,72 tok/s TG Prefill 3.178 · TTFT 5.437 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 247,85 tok/s TG Prefill 2.967 · TTFT 3.756 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 29 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 242,43 tok/s TG Prefill 4.599 · TTFT 2.157 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 30 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 240,22 tok/s TG Prefill 7.577 · TTFT 4.168 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 31 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 238,79 tok/s TG Prefill 5.303 · TTFT 5.204 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 32 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,40 tok/s TG Prefill 7.121 · TTFT 4.462 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 33 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,22 tok/s TG Prefill 6.992 · TTFT 4.523 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 34 | Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 227,38 tok/s TG Prefill 13.749 · TTFT 177 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 35 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 225,93 tok/s TG Prefill 1.021 · TTFT 8.456 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,62 tok/s TG Prefill 1.136 · TTFT 15.201 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,61 tok/s TG Prefill 2.963 · TTFT 3.827 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 38 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 215,49 tok/s TG Prefill 2.912 · TTFT 3.858 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 39 | Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 215,46 tok/s TG Prefill 3.907 · TTFT 5.778 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 40 | Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,81 tok/s TG Prefill 3.032 · TTFT 3.678 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 41 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,67 tok/s TG Prefill 6.514 · TTFT 1.882 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 42 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 210,14 tok/s TG Prefill 4.085 · TTFT 5.519 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 43 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,60 tok/s TG Prefill 3.450 · TTFT 2.889 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 44 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 199,14 tok/s TG Prefill 5.601 · TTFT 2.464 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 45 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,77 tok/s TG Prefill 4.023 · TTFT 5.609 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 46 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,76 tok/s TG Prefill 3.994 · TTFT 5.630 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 47 | Ornith-1.5-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 196,95 tok/s TG Prefill 4.698 · TTFT 4.796 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 48 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,56 tok/s TG Prefill 3.011 · TTFT 2.862 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,52 tok/s TG Prefill 3.923 · TTFT 3.136 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 50 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,37 tok/s TG Prefill 4.316 · TTFT 6.560 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 51 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,11 tok/s TG Prefill 3.767 · TTFT 3.939 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 52 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 192,64 tok/s TG Prefill 5.318 · TTFT 2.482 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 53 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 189,78 tok/s TG Prefill 4.641 · TTFT 2.817 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 54 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,76 tok/s TG Prefill 629 · TTFT 31.617 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 55 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,69 tok/s TG Prefill 4.792 · TTFT 2.726 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 56 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,18 tok/s TG Prefill 1.748 · TTFT 10.113 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,28 tok/s TG Prefill 3.436 · TTFT 3.015 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 58 | gemma-3n-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 176,12 tok/s TG Prefill 3.846 · TTFT 2.574 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 59 | Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 171,83 tok/s TG Prefill 1.188 · TTFT 16.950 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 60 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,09 tok/s TG Prefill 6.490 · TTFT 2.083 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 61 | Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 166,21 tok/s TG Prefill 2.966 · TTFT 3.382 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 62 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 159,65 tok/s TG Prefill 3.083 · TTFT 3.258 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 63 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 159,14 tok/s TG Prefill 3.065 · TTFT 3.273 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 64 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 157,95 tok/s TG Prefill 3.108 · TTFT 3.229 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 65 | Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 156,39 tok/s TG Prefill 9.842 · TTFT 248 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 66 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 151,97 tok/s TG Prefill 7.125 · TTFT 2.029 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 67 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 145,30 tok/s TG Prefill 1.554 · TTFT 19.578 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 68 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 142,79 tok/s TG Prefill 4.374 · TTFT 10.633 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 69 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 141,77 tok/s TG Prefill 3.307 · TTFT 10.899 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 70 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 139,86 tok/s TG Prefill 1.753 · TTFT 5.039 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Ornith-1.5-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 139,16 tok/s TG Prefill 3.596 · TTFT 2.796 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 72 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,88 tok/s TG Prefill 2.354 · TTFT 9.328 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 73 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 135,40 tok/s TG Prefill 2.502 · TTFT 11.327 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 74 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,08 tok/s TG Prefill 3.434 · TTFT 9.975 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 75 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,28 tok/s TG Prefill 2.178 · TTFT 988 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 76 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 128,96 tok/s TG Prefill 4.924 · TTFT 402 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 77 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,55 tok/s TG Prefill 5.151 · TTFT 2.489 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 78 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 120,65 tok/s TG Prefill 3.944 · TTFT 501 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 79 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,88 tok/s TG Prefill 3.109 · TTFT 3.967 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 80 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,98 tok/s TG Prefill 5.227 · TTFT 378 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 81 | Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,36 tok/s TG Prefill 1.455 · TTFT 15.755 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 82 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,53 tok/s TG Prefill 1.848 · TTFT 16.560 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 83 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,26 tok/s TG Prefill 1.865 · TTFT 16.524 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 84 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 115,65 tok/s TG Prefill 1.214 · TTFT 20.637 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 85 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,99 tok/s TG Prefill 1.982 · TTFT 16.358 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 86 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,83 tok/s TG Prefill 1.430 · TTFT 6.923 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 87 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,56 tok/s TG Prefill 2.551 · TTFT 851 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 88 | Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,45 tok/s TG Prefill 2.607 · TTFT 827 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 89 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 110,73 tok/s TG Prefill 2.564 · TTFT 841 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 90 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,38 tok/s TG Prefill 7.256 · TTFT 344 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 91 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,85 tok/s TG Prefill 2.620 · TTFT 821 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 92 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,77 tok/s TG Prefill 3.358 · TTFT 726 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 93 | Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,74 tok/s TG Prefill 1.377 · TTFT 16.495 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 94 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,90 tok/s TG Prefill 3.563 · TTFT 686 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 95 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,64 tok/s TG Prefill 3.403 · TTFT 719 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 96 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,62 tok/s TG Prefill 5.798 · TTFT 343 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 97 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,11 tok/s TG Prefill 3.281 · TTFT 744 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 98 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,91 tok/s TG Prefill 3.258 · TTFT 750 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 99 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,40 tok/s TG Prefill 768 · TTFT 2.243 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 100 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 93,40 tok/s TG Prefill 3.060 · TTFT 3.167 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 101 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 93,07 tok/s TG Prefill 7.599 · TTFT 324 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 102 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,04 tok/s TG Prefill 3.064 · TTFT 897 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 103 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,68 tok/s TG Prefill 2.867 · TTFT 6.226 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 104 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,06 tok/s TG Prefill 3.482 · TTFT 6.548 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 105 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,96 tok/s TG Prefill 3.088 · TTFT 641 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 106 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,07 tok/s TG Prefill 5.545 · TTFT 440 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 107 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,75 tok/s TG Prefill 1.512 · TTFT 1.139 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 108 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,10 tok/s TG Prefill 6.957 · TTFT 7.450 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 109 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,60 tok/s TG Prefill 1.791 · TTFT 6.870 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 110 | Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,10 tok/s TG Prefill 2.330 · TTFT 828 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 111 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,06 tok/s TG Prefill 2.578 · TTFT 5.626 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 112 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 74,57 tok/s TG Prefill 2.319 · TTFT 7.067 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 113 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 74,39 tok/s TG Prefill 1.748 · TTFT 11.355 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 114 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,77 tok/s TG Prefill 2.423 · TTFT 797 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 115 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,71 tok/s TG Prefill 2.390 · TTFT 807 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 116 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,58 tok/s TG Prefill 2.478 · TTFT 778 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 117 | Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,58 tok/s TG Prefill 1.050 · TTFT 9.383 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 118 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,93 tok/s TG Prefill 2.843 · TTFT 920 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 119 | gemma-3n-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 65,22 tok/s TG Prefill 3.462 · TTFT 571 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 120 | Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,07 tok/s TG Prefill 985 · TTFT 10.349 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 121 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,07 tok/s TG Prefill 2.204 · TTFT 932 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 122 | Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,57 tok/s TG Prefill 1.027 · TTFT 9.755 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 123 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,79 tok/s TG Prefill 4.166 · TTFT 593 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 124 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,59 tok/s TG Prefill 1.147 · TTFT 1.541 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 125 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,43 tok/s TG Prefill 4.133 · TTFT 598 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 126 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,62 tok/s TG Prefill 1.539 · TTFT 9.403 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 127 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,60 tok/s TG Prefill 1.544 · TTFT 9.340 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 128 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,29 tok/s TG Prefill 1.532 · TTFT 9.444 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 129 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,78 tok/s TG Prefill 1.962 · TTFT 6.490 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 130 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,41 tok/s TG Prefill 1.260 · TTFT 19.903 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 131 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,69 tok/s TG Prefill 1.580 · TTFT 1.250 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 132 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,43 tok/s TG Prefill 2.188 · TTFT 1.034 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 133 | Ornith-1.5-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,42 tok/s TG Prefill 2.788 · TTFT 691 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 134 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,35 tok/s TG Prefill 778 · TTFT 25.706 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 135 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,87 tok/s TG Prefill 1.491 · TTFT 7.113 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 136 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,44 tok/s TG Prefill 896 · TTFT 12.716 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 137 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 36,37 tok/s TG Prefill 928 · TTFT 13.981 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 138 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,13 tok/s TG Prefill 2.320 · TTFT 975 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 139 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,61 tok/s TG Prefill 1.301 · TTFT 1.735 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 140 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,50 tok/s TG Prefill 1.317 · TTFT 1.755 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 141 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,45 tok/s TG Prefill 1.304 · TTFT 2.089 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 142 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,37 tok/s TG Prefill 2.019 · TTFT 1.676 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 143 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,37 tok/s TG Prefill 1.631 · TTFT 1.662 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 144 | Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,32 tok/s TG Prefill 999 · TTFT 1.966 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 145 | Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,39 tok/s TG Prefill 886 · TTFT 2.232 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 146 | Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,14 tok/s TG Prefill 871 · TTFT 2.219 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 147 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,61 tok/s TG Prefill 911 · TTFT 2.703 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 148 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,60 tok/s TG Prefill 916 · TTFT 2.675 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 149 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,51 tok/s TG Prefill 888 · TTFT 2.770 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 150 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,89 tok/s TG Prefill 787 · TTFT 2.807 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |