AMD Radeon RX 6900 XT × Mistral Nemo Instruct 2407
Mistral Nemo Instruct 2407 on AMD Radeon RX 6900 XT
27.1best gen tok/s
832best prompt tok/s
640max context tested
4results
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 | 27.1 | 746 | LocalScore ↗ | 512+128 | 1,904 ms | llamafile 0.9.2 |
| Q5_K - Medium | 25.4 | 717 | LocalScore ↗ | 512+128 | 1,873 ms | llamafile 0.9.2 |
| Q6_K | 23.8 | 647 | LocalScore ↗ | 512+128 | 2,063 ms | llamafile 0.9.2 |
| Q8_0 | 20.7 | 832 | LocalScore ↗ | 512+128 | 1,667 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 AMD Radeon RX 6900 XT 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.