LM Studio on the M5 Max 36GB
llamaperf has 3 LM Studio reports on the M5 Max 36GB, 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 LM Studio reports on the M5 Max 36GB
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.
- Qwen3.6 · 4-bit124.5 t/s
- Qwen3.5 · 4-bit81.1 t/s
- Qwen3.8 · 4-bit26.0 t/s
Frequently asked
How fast is LM Studio on the M5 Max 36GB?
llamaperf has 3 LM Studio reports on the M5 Max 36GB, 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.