Ollama on the M4 32GB
llamaperf has 7 Ollama reports on the M4 32GB, 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.
7 Ollama reports on the M4 32GB
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.
- Gemma 4 · Q4_K_M5.3 t/s
- Gemma 4 · Q4_K_M32.0 t/s
- Gemma 4 · Q4_K_M12.5 t/s
- Gemma 4 · Q4_K_M29.9 t/s
- Gemma 4 · Q4_K_M55.0 t/s
- Gemma 4 · Q4_K_M8.7 t/s
- Gemma 4 · Q4_K_M16.7 t/s
Frequently asked
How fast is Ollama on the M4 32GB?
llamaperf has 7 Ollama reports on the M4 32GB, 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.