llamaperf
Submit

M3 Pro 18GB

APPLE · 18GB unified memory · 1 report

On the M3 Pro 18GB, Qwen3 8B at 4-bit, the model most run on it, generates a median of 25.2 tokens per second from one plain run (community reports, as of 30 Oct 2026).

As of 30 Oct 2026, the models most run on the M3 Pro 18GB, with generation and prompt-processing medians from plain runs (one device, one request, no speculative decoding):

Engines people use on it: llama.cpp 1 (reports)

See reported performanceEstimate what fits
How to compare these reports →Filter reports by setup →All M3 Macs compared →

Run models on your M3 Pro 18GB? 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 agentPaste a result

Reported performance on the M3 Pro 18GB

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 18 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 8B

M3 Pro 18GB · llama.cpp · 1,024 ctx

Tone: mixedApple hardware
generation:
25.2 tokens/s
quant:
Q4_K_M (GGUF)

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.

summarizationtool-use

User benchmarks Qwen3-8B at 25.2 tok/s on an M3 Pro 18GB. Setup is llama.cpp b11246 with Q4_K_M and 1024-token input, 256 output tokens, single request. Runs were taken under memory pressure so absolute speeds are pessimistic; MLX-LM reaches 35.5 tok/s at 4 concurrent requests while llama.cpp plateaus at 21.0.

Oct 7, 2026

Get a weekly email of new M3 Pro 18GB 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 / hardwareQuant / engineReported contextGeneration
Qwen3 8B
M3 Pro 18GB
Q4_K_M
llama.cpp
1,02425.2 tokens/s

Frequently asked

How fast is the M3 Pro 18GB for local LLMs?

On the M3 Pro 18GB, Qwen3 8B at 4-bit, the model most run on it, generates a median of 25.2 tokens per second from one plain run (community reports, as of 30 Oct 2026).