M2 Max (30 GPU)
16 records across 3 models (quants: F16, IQ3_S, Q4_0, Q4_K_M, Q8_0, unspecified).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Max (30 GPU) | llama 7B | Q4_0 | llama.cpp (Metal) | 60.99 | 537.6 | – | – | – | 2023-11-22 | community | – | source |
| M2 Max (30 GPU) | llama 7B | Q8_0 | llama.cpp (Metal) | 39.97 | 540.15 | – | – | – | 2023-11-22 | community | – | source |
| M2 Max (30 GPU) | llama 7B | F16 | llama.cpp (Metal) | 24.16 | 600.46 | – | – | – | 2023-11-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.6-35B-A3B | Q4_K_M | llama.cpp (Metal) | 58.56 | 671.40 | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | unspecified | llama.cpp (Metal) | 46.2 | – | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | unspecified | llama.cpp (Metal) | 34.6 | – | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | unspecified | llama.cpp (Metal) | 29.4 | – | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | unspecified | llama.cpp (Metal) | 20.1 | – | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | unspecified | llama.cpp (Metal) | 17.1 | – | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 10.82 | 106.78 | – | – | tg128 | 2026-09-22 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 10.53 | – | – | – | tg128 | 2026-09-28 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 10.3 | – | – | – | tg128 | 2026-09-28 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 10.29 | – | – | – | tg128 | 2026-09-28 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 10.18 | – | – | – | tg128 | 2026-09-28 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 9.81 | – | – | – | tg128 | 2026-09-28 | community | – | source |
| M2 Max (30 GPU) | Qwen3.8-27B | IQ3_S | llama.cpp (Metal) | 6.13 | – | – | – | tg128 | 2026-09-28 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085