RTX 4000 SFF Ada Generation × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on RTX 4000 SFF Ada Generation
191best gen tok/s
8,786best 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 | 191 | 8,762 | LocalScore ↗ | 512+128 | 181 ms | llamafile 0.9.2 |
| Q4_K - Medium | 189 | 8,786 | LocalScore ↗ | 512+128 | 179 ms | llamafile 0.9.2 |
| Q4_K - Medium | 188 | 8,712 | LocalScore ↗ | 512+128 | 177 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 4000 SFF Ada Generation 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.