AMD Radeon RX 7800 XT × Qwen2.5 14B Instruct
Qwen2.5 14B Instruct on AMD Radeon RX 7800 XT
23.0best gen tok/s
316best 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 | 23.0 | 302 | LocalScore ↗ | 512+128 | 4,354 ms | llamafile 0.9.2 |
| Q4_K - Medium | 23.0 | 302 | LocalScore ↗ | 512+128 | 4,164 ms | llamafile 0.9.2 |
| Q4_K - Medium | 23.0 | 316 | LocalScore ↗ | 512+128 | 4,216 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.7 | 301 | LocalScore ↗ | 512+128 | 4,311 ms | llamafile 0.9.3 |
| Q4_K - Medium | 21.3 | 171 | LocalScore ↗ | 4,352 | 8,900 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 7800 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.