AMD Radeon RX 6650 XT × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on AMD Radeon RX 6650 XT
109best gen tok/s
3,031best prompt tok/s
640max context tested
6results
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 | 109 | 3,031 | LocalScore ↗ | 512+128 | 443 ms | llamafile 0.9.1 |
| Q4_K - Medium | 84.0 | 2,494 | LocalScore ↗ | 512+128 | 621 ms | llamafile 0.9.2 |
| Q4_K - Medium | 83.9 | 2,606 | LocalScore ↗ | 512+128 | 617 ms | llamafile 0.9.2 |
| Q4_K - Medium | 83.0 | 2,592 | LocalScore ↗ | 512+128 | 620 ms | llamafile 0.9.2 |
| Q4_K - Medium | 82.3 | 2,475 | LocalScore ↗ | 512+128 | 620 ms | llamafile 0.9.2 |
| Q4_K - Medium | 82.2 | 2,600 | LocalScore ↗ | 512+128 | 623 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 6650 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.