AMD Radeon RX 6700 XT × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on AMD Radeon RX 6700 XT
103best gen tok/s
3,192best prompt tok/s
4,352max context tested
5results
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 | 103 | 3,192 | LocalScore ↗ | 512+128 | 489 ms | llamafile 0.9.2 |
| Q4_K - Medium | 101 | 3,088 | LocalScore ↗ | 512+128 | 506 ms | llamafile 0.9.3 |
| Q4_K - Medium | 92.5 | 3,054 | LocalScore ↗ | 512+128 | 510 ms | llamafile 0.9.2 |
| Q4_K - Medium | 12.8 | 2,552 | LocalScore ↗ | 512+128 | 644 ms | llamafile 0.9.2 |
| Q4_K - Medium | 12.4 | 2,532 | LocalScore ↗ | 4,352 | 654 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 6700 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.