M4 Max 48GB

APPLE · 48GB unified memory · 1 report

On the M4 Max 48GB, Qwen3.5 4B at 4-bit, the model most run on it, generates a median of 85.0 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 M4 Max 48GB, with generation and prompt-processing medians from plain runs (one device, one request, no speculative decoding):

Qwen3.5 4B
85.0gen t/s at 4-bit · one run

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

See reported performance Estimate what fits

How to compare these reports →Filter reports by setup →All M4 Macs compared →

Run models on your M4 Max 48GB? 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 M4 Max 48GB

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 48 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

Qwen3.5 4B

M4 Max 48GB · llama.cpp

generation:: 85.0 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 reports Qwen3.5 4B at ~85 tok/s decode on an M4 Max 48GB, running a Mac meeting notetaker stack. Setup is llama.cpp with Q4_K_M weights; the full on-device stack totals 6.8 GB across five models. A 26-minute meeting produced finished notes in 33 s warm. Speaker error dropped from 43.4% to 14.6% DER on AMI, and autocomplete p95 improved from 1.83 s to 0.49 s. MiniCPM5 2B was tried for notes but repeated itself and misassigned action items, so Qwen3.5 4B stayed the default.

Get a weekly email of new M4 Max 48GB 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
Qwen3.5 4B M4 Max 48GB	Q4_K_M llama.cpp	Not reported	85.0 tokens/s

Frequently asked

How fast is the M4 Max 48GB for local LLMs?

On the M4 Max 48GB, Qwen3.5 4B at 4-bit, the model most run on it, generates a median of 85.0 tokens per second from one plain run (community reports, as of 30 Oct 2026).