AMD Radeon RX 6800 XT × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on AMD Radeon RX 6800 XT
118best gen tok/s
4,655best 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 | 118 | 4,655 | LocalScore ↗ | 512+128 | 326 ms | llamafile 0.9.3 |
| Q4_K - Medium | 110 | 4,585 | LocalScore ↗ | 512+128 | 331 ms | llamafile 0.9.2 |
| Q4_K - Medium | 96.1 | 4,565 | LocalScore ↗ | 512+128 | 329 ms | llamafile 0.9.2 |
| Q4_K - Medium | 12.1 | 3,324 | LocalScore ↗ | 512+128 | 557 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 6800 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.