llama.cpp on the M4 Pro 24GB
llamaperf has 3 llama.cpp reports on the M4 Pro 24GB, 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.
3 llama.cpp reports on the M4 Pro 24GB
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 0.6B · Q4297.4 t/s
- Qwen3-Next 80B · 3B active · Q4_K_M2.9 t/s(part in system RAM)
- Qwen3.8 27B · Q4_K_M11.4 t/s
Frequently asked
How fast is llama.cpp on the M4 Pro 24GB?
llamaperf has 3 llama.cpp reports on the M4 Pro 24GB, 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.