🏆
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 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.758,55 tok/s TG Prefill 13.889 · TTFT 5.964 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.606,09 tok/s TG Prefill 12.150 · TTFT 6.323 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.423,31 tok/s TG Prefill 10.739 · TTFT 6.965 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.421,79 tok/s TG Prefill 12.418 · TTFT 6.980 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.082,39 tok/s TG Prefill 6.941 · TTFT 9.659 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.022,79 tok/s TG Prefill 18.744 · TTFT 2.204 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 7 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 983,68 tok/s TG Prefill 7.362 · TTFT 10.840 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 8 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 914,25 tok/s TG Prefill 12.655 · TTFT 1.885 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 892,60 tok/s TG Prefill 10.513 · TTFT 2.066 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 10 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 812,02 tok/s TG Prefill 8.201 · TTFT 2.420 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 771,00 tok/s TG Prefill 12.156 · TTFT 2.143 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 616,01 tok/s TG Prefill 13.778 · TTFT 803 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 13 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 592,13 tok/s TG Prefill 5.662 · TTFT 3.385 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 542,58 tok/s TG Prefill 6.522 · TTFT 3.407 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 15 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 488,18 tok/s TG Prefill 4.229 · TTFT 20.915 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 484,77 tok/s TG Prefill 4.124 · TTFT 21.088 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 474,76 tok/s TG Prefill 1.760 · TTFT 26.540 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 18 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 455,06 tok/s TG Prefill 3.954 · TTFT 21.269 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 428,56 tok/s TG Prefill 6.452 · TTFT 3.073 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 20 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 375,94 tok/s TG Prefill 6.660 · TTFT 2.979 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 21 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 346,29 tok/s TG Prefill 16.028 · TTFT 1.776 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMvllm bf16 | Details → | |
| 22 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 283,39 tok/s TG Prefill 6.346 · TTFT 1.565 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 23 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 267,65 tok/s TG Prefill 1.544 · TTFT 9.962 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 24 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 254,04 tok/s TG Prefill 6.450 · TTFT 1.538 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 25 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 251,39 tok/s TG Prefill 3.708 · TTFT 6.599 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 247,94 tok/s TG Prefill 3.881 · TTFT 514 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,68 tok/s TG Prefill 3.165 · TTFT 7.126 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,53 tok/s TG Prefill 9.711 · TTFT 204 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,62 tok/s TG Prefill 3.740 · TTFT 6.690 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 223,39 tok/s TG Prefill 4.911 · TTFT 482 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 208,96 tok/s TG Prefill 7.261 · TTFT 272 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 177,40 tok/s TG Prefill 11.718 · TTFT 941 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMvllm bf16 | Details → | |
| 33 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 165,04 tok/s TG Prefill 2.897 · TTFT 711 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 155,81 tok/s TG Prefill 6.094 · TTFT 325 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 35 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,58 tok/s TG Prefill 7.078 · TTFT 281 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 36 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,73 tok/s TG Prefill 1.652 · TTFT 12.206 ms | 10× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 37 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 125,06 tok/s TG Prefill 1.687 · TTFT 12.063 ms | 10× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 38 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,55 tok/s TG Prefill 5.239 · TTFT 378 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 39 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 97,08 tok/s TG Prefill 757 · TTFT 13.077 ms | 5× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 40 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,22 tok/s TG Prefill 1.480 · TTFT 6.689 ms | 5× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 41 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 93,25 tok/s TG Prefill 1.437 · TTFT 6.874 ms | 5× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 42 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,28 tok/s TG Prefill 5.229 · TTFT 378 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 43 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,70 tok/s TG Prefill 1.022 · TTFT 2.264 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 44 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,50 tok/s TG Prefill 2.576 · TTFT 769 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,50 tok/s TG Prefill 1.862 · TTFT 1.599 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,96 tok/s TG Prefill 818 · TTFT 24.766 ms | 10× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 47 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 53,35 tok/s TG Prefill 1.366 · TTFT 1.447 ms | 1× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 48 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 43,23 tok/s TG Prefill 758 · TTFT 2.613 ms | 1× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 49 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,32 tok/s TG Prefill 1.088 · TTFT 1.818 ms | 1× | 2x NVIDIA GeForce RTX 2060Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz · 7 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 50 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,86 tok/s TG Prefill 6.286 · TTFT 315 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMvllm bf16 | Details → |