RTX 6000 Ada
28 records across 7 models (quants: MXFP4, Q4_K, Ternary PQ2_0, Ternary PTQ1_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 6000 Ada | gpt-oss 20B 20B | MXFP4 | llama.cpp | 160.8 | 6495.8 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | gpt-oss 20B 20B | MXFP4 | llama.cpp | 137.1 | 5350.5 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | gpt-oss 20B 20B | MXFP4 | llama.cpp | 116.3 | 3818.7 | – | – | 32768 | – | sourced | – | source |
| RTX 6000 Ada | gpt-oss 20B 20B | MXFP4 | llama.cpp | 88.4 | 2270.3 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | gpt-oss 20B 20B | MXFP4 | llama.cpp | 57.5 | 1177.7 | – | – | 131072 | – | sourced | – | source |
| RTX 6000 Ada | Llama 3.3 70B 70B | Q4_K | llama.cpp | 18.1 | 678.1 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Llama 3.3 70B 70B | Q4_K | llama.cpp | 13.7 | 526.0 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 14B 14B | Q4_K | llama.cpp | 81.2 | 2912.1 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 14B 14B | Q4_K | llama.cpp | 58.5 | 2367.2 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 14B 14B | Q4_K | llama.cpp | 42.3 | 1310.2 | – | – | 32768 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 14B 14B | Q4_K | llama.cpp | 27.0 | 727.4 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 14B 14B | Q4_K | llama.cpp | 15.2 | 358.6 | – | – | 131072 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 30B A3B 30B | Q4_K | llama.cpp | 199.6 | 3888.0 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 30B A3B 30B | Q4_K | llama.cpp | 120.1 | 3156.5 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 30B A3B 30B | Q4_K | llama.cpp | 74.3 | 2010.6 | – | – | 32768 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 30B A3B 30B | Q4_K | llama.cpp | 40.8 | 913.2 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 30B A3B 30B | Q4_K | llama.cpp | 20.7 | 448.6 | – | – | 131072 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 32B 32B | Q4_K | llama.cpp | 37.4 | 1203.9 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 32B 32B | Q4_K | llama.cpp | 25.1 | 977.5 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 32B 32B | Q4_K | llama.cpp | 18.2 | 595.5 | – | – | 32768 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 32B 32B | Q4_K | llama.cpp | 11.8 | 348.6 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 133.9 | 4932.5 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 98.7 | 4096.4 | – | – | 16384 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 68.9 | 2218.5 | – | – | 32768 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 39.9 | 1152.6 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 20.8 | 541.3 | – | – | 131072 | – | sourced | – | source |
| RTX 6000 Ada | Ternary-Bonsai-2-27B | Ternary PTQ1_0 | llama.cpp (CUDA) | 90.4 | 1657 | – | – | tg128 | 2026-09-16 | community | – | source |
| RTX 6000 Ada | Ternary-Bonsai-2-27B | Ternary PQ2_0 | llama.cpp (CUDA) | 82.8 | 2431 | – | – | tg128 | 2026-09-16 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085