Radeon RX 7900 XT × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on Radeon RX 7900 XT
132best gen tok/s
6,502best 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 | 132 | 4,185 | LocalScore ↗ | 512+128 | 312 ms | llamafile 0.9.2 |
| Q4_K - Medium | 131 | 4,184 | LocalScore ↗ | 512+128 | 313 ms | llamafile 0.9.2 |
| Q4_K - Medium | 34.6 | 6,502 | LocalScore ↗ | 512+128 | 216 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 Radeon RX 7900 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.