llama.cpp on the M1 Max 64GB
llamaperf has 4 llama.cpp reports on the M1 Max 64GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
4 llama.cpp reports on the M1 Max 64GB
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3-Coder 30B · 3B active · Q4_K_M64.4 t/s
- Model not identified · IQ2_XS0.9 t/s
- DeepSeek V4 Flash 284B · 13B active · IQ3-XXS8.0 t/s(part in system RAM)
- Qwen3.8 125B · 6B active · Q4PP 180.0 t/s
Frequently asked
How fast is llama.cpp on the M1 Max 64GB?
llamaperf has 4 llama.cpp reports on the M1 Max 64GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.