M3 Max 96GB

APPLE · 96GB unified memory · 2 reports

On the M3 Max 96GB, Qwen3.6 27B at 8-bit, the model most run on it, generates a median of 7.4 tokens per second from one plain run (community reports, as of 29 Oct 2026).

As of 29 Oct 2026, the models most run on the M3 Max 96GB, with generation and prompt-processing medians from plain runs (one device, one request, no speculative decoding):

Qwen3.6 27B
7.4gen t/s at 8-bit · one run
PP 121.3 t/s · 1 run

Engines people use on it: ds4 1 (reports) · oMLX 1 (reports)

See reported performance Estimate what fits

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

Run models on your M3 Max 96GB? 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 Max 96GB

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 96 GB of unified memory.

This page is thin (2 of 3 reports needed for indexing). Help fill it in.

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

Qwen3.6 27B

M3 Max 96GB · oMLX

generation:: 7.4 tokens/s
prompt processing (prefill):: 121.3 tokens/s
quant:: 8bit (MLX)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.

User reports Qwen3.6 27B at 7.4 t/s generation and 121.3 t/s prompt processing on an M3 Max 96GB. Setup is oMLX with the MLX 8-bit model at pp1024/tg128, using 28.34 GB peak memory. A pp4096/tg128 run reached 8.8 t/s generation and 133.8 t/s prompt processing. Continuous batching at 4x reached 19.9 t/s aggregate generation. User is new to LLMs and asks whether the slow speed is due to the dense model or a setup problem.

DeepSeek V4 Flash 284B (13B active)

M3 Max 96GB · ds4

generation:: 12.7 tokens/s

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.

User reports DeepSeek V4 Flash at 11-13 t/s on an M3 Max 96GB with SSD streaming and iogpu.wired_limit_mb=86016. Setup is antirez's ds4 engine with GGUF. TTFT is 3-5s after warmup. Prefill of 36k tokens takes about 2.5 minutes.

Get a weekly email of new M3 Max 96GB 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
Qwen3.6 27B M3 Max 96GB	8bit oMLX	Not reported	7.4 tokens/s
DeepSeek V4 Flash 284B (13B active) M3 Max 96GB	Not reported ds4	Not reported	12.7 tokens/s

Frequently asked

How fast is the M3 Max 96GB for local LLMs?

On the M3 Max 96GB, Qwen3.6 27B at 8-bit, the model most run on it, generates a median of 7.4 tokens per second from one plain run (community reports, as of 29 Oct 2026).