🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | 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 → | |
| 2 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 207,89 tok/s TG Prefill 6.462 · TTFT 4.062 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | 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 → | |
| 4 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 157,77 tok/s TG Prefill 4.563 · TTFT 2.532 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | 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 → | |
| 6 | Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,48 tok/s TG Prefill 2.514 · TTFT 862 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAM | llama.cppgodclawQ4_K_M | Details → |