llamaperf

M6 24GB

APPLE · 24GB unified memory · 1 report

Is this your card?

On the M6 24GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 9.8 tokens per second from one plain run (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, the models most run on the M6 24GB, each one size at one quant level, with the median generation speed of its plain runs (one device, one request, no speculative decoding):

Bars are medians on one scale, 0 to 9.8 tokens/s. Press ▶ to watch text arrive at a row's speed.

Engines people use on it: mlx-vlm 1 (reports)

Run models on your M6 24GB? 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.

Reported performance on the M6 24GB

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 24 GB of unified memory. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

One report on this card so far, so treat the figures as early. Add yours.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Apple hardware
generation:
9.8 tokens/s
quant:
4bit (MLX)
mtp (multi-token prediction):
off
summarization

User reports Qwen3.8 27B at 9.83 t/s generation on a Mac mini M6 24GB, from a 525-token prompt. Setup is mlx-vlm 0.7.3 with the mlx-community 4-bit checkpoint, one request, speculative decoding off. This is the plain baseline from a single run in the author's MTP comparison. The 268 t/s prefill in the source is the prompt divided by time to first token, so no prompt speed is stored.

Oct 9, 2026

Get a weekly email of new M6 24GB 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
Qwen3.8 27B dense
M6 24GB
4bit
mlx-vlm
Not reported9.8 tokens/s

Frequently asked

How fast is the M6 24GB for local LLMs?

On the M6 24GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 9.8 tokens per second from one plain run (community reports, as of 22 Nov 2026).