AMD Radeon RX 6600 × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on AMD Radeon RX 6600
20.8best gen tok/s
424best prompt tok/s
4,352max 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 | 20.8 | 418 | LocalScore ↗ | 512+128 | 3,805 ms | llamafile 0.9.3 |
| Q4_K - Medium | 5.2 | 424 | LocalScore ↗ | 512+128 | 3,380 ms | llamafile 0.9.3 |
| Q4_K - Medium | 4.7 | 415 | LocalScore ↗ | 4,352 | 3,425 ms | llamafile 0.9.3 |
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 6600 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.