M3 Pro 36GB

APPLE · 36GB unified memory · 1 report

See reported performance Estimate what fits

How to compare these reports →Filter reports by setup →All M3 Macs compared →

Run models on your M3 Pro 36GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Benchmark with your agent Paste a result

Reported performance on the M3 Pro 36GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 36 GB of unified memory.

This page is thin (1 of 3 reports needed for indexing). Help fill it in.

Date ↓Date ↑Token speed ↓Token speed ↑Prefill ↓Prefill ↑Context ↓Context ↑Ranked

Qwen3.8 27B

M3 Pro 36GB · custom C + Metal runtime

generation:: 17.7 tokens/s
quant:: Q4

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

codingsummarization

User reports a custom C + Metal runtime with speculative decoding at 18 t/s end-to-end on coding tasks and 17.7 t/s for an LRUCache implementation, on 36 GB unified memory. Q4 weights are about 15 GB, mmap'd. Prose runs at roughly 10-11 t/s. TTFT is about 1.4s for a short prompt and about 2.7s for a 128-token prompt. The user compares the custom runtime against llama.cpp and reports it faster.

Get a weekly email of new M3 Pro 36GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardware	Quant / engine	Reported context	Generation
Qwen3.8 27B M3 Pro 36GB	Q4 custom C + Metal runtime	Not reported	17.7 tokens/s