Apple M3 Ultra (80-core GPU) × Llama 2 7B
Llama 2 7B on Apple M3 Ultra (80-core GPU)
92.1best gen tok/s
1,538best 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_0 | 92.1 | 1,471 | llama.cpp (Metal) ↗ | 512+128 | — | llama.cpp Metal |
| Q8_0 | 63.9 | 1,488 | llama.cpp (Metal) ↗ | 512+128 | — | llama.cpp Metal |
| F16 | 39.8 | 1,538 | llama.cpp (Metal) ↗ | 512+128 | — | llama.cpp Metal |
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.