RTX PRO 6000 Blackwell × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on RTX PRO 6000 Blackwell
374best gen tok/s
30,896best prompt tok/s
640max context tested
3results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 374 | 30,896 | LocalScore ↗ | 512+128 | 43 ms | llamafile 0.9.2 |
| Q4_K - Medium | 114 | 19,907 | LocalScore ↗ | 512+128 | 66 ms | llamafile 0.9.2 |
| Q4_K - Medium | 106 | 18,081 | LocalScore ↗ | 512+128 | 74 ms | llamafile 0.9.2 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can RTX PRO 6000 Blackwell run? →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.