AMD Radeon 780M Graphics × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on AMD Radeon 780M Graphics
12.1best gen tok/s
690best prompt tok/s
640max context tested
7results
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 | 12.1 | 632 | LocalScore ↗ | 512+128 | 2,051 ms | llamafile 0.9.3 |
| Q4_K - Medium | 11.8 | 666 | LocalScore ↗ | 512+128 | 1,962 ms | llamafile 0.9.2 |
| Q4_K - Medium | 11.7 | 690 | LocalScore ↗ | 512+128 | 1,881 ms | llamafile 0.9.2 |
| Q4_K - Medium | 11.5 | 617 | LocalScore ↗ | 512+128 | 2,094 ms | llamafile 0.9.3 |
| Q4_K - Medium | 11.2 | 572 | LocalScore ↗ | 512+128 | 2,316 ms | llamafile 0.9.3 |
| Q4_K - Medium | 7.5 | 506 | LocalScore ↗ | 512+128 | 2,644 ms | llamafile 0.9.3 |
| Q4_K - Medium | 5.9 | 399 | LocalScore ↗ | 512+128 | 3,356 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 780M Graphics 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.