Models

Qwen3 235B A22B

Alibaba Qwen · April 2025

Get

Hugging Face

A 235B, 22B active chat model from Alibaba Qwen.

Rating: 3.8
Downloads: 18K
Likes: 95
Parameters: 235B, 22B active
Context: 40K
Licence: apache-2.0

Too big for this Mac

Its smallest size needs 89 GB of memory, more than M4 · 16 GB can give it.

Ratings

3.8 out of 5, across people's blind votes on its answers and the tests below.

Text: 1375
Coding: 1431

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

KnowledgeMMLU-Pro: 68.2%

MMLU-Pro: graduate-level questions in 14 subjects. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.

Qwen3 235B A22B runs well from a Mac with an M1 Ultra and 128 GB of memory. 10 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From Qwen/Qwen3-235B-A22B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

Size	Download	Memory at 8K	Get
Q4_K_M	142 GB	143 GBestimated	Open
Q5_0	162 GB	163 GBestimated	Open
Q5_K_M	167 GB	168 GBestimated	Open
Q6_K	193 GB	194 GBestimated	Open
Q8_0	250 GB	251 GBestimated	Open

Run It Anywhere

Qwen3 235B A22B is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from Qwen straight from Hugging Face.

LM StudioMac, Windows, LinuxOpen
JanMac, Windows, LinuxOpen
MstyMac, Windows, LinuxOpen
OllamaMac, Windows, Linuxollama run hf.co/Qwen/Qwen3-235B-A22B-GGUF:Q4_K_M
llama.cppMac, Windows, Linuxllama-server -hf Qwen/Qwen3-235B-A22B-GGUF:Q4_K_M
Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/Qwen/Qwen3-235B-A22B-GGUF:Q4_K_M

On a PC Graphics Card

Video memory	Largest size that fits	Memory at 8K
6 GB	None worth running	needs 143 GB
8 GB	None worth running	needs 143 GB
10 GB	None worth running	needs 143 GB
11 GB	None worth running	needs 143 GB
12 GB	None worth running	needs 143 GB
16 GB	None worth running	needs 143 GB
20 GB	None worth running	needs 143 GB
24 GB	None worth running	needs 143 GB
32 GB	None worth running	needs 143 GB
48 GB	None worth running	needs 143 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac

Mac	Size	Fit	Memory	Writes
M6 · 16 GB	Q2_K	Too big	89 GB
M6 · 24 GB	Q2_K	Too big	89 GB
M6 · 32 GB	Q2_K	Too big	89 GB
M5 · 16 GB	Q2_K	Too big	89 GB
M5 · 24 GB	Q2_K	Too big	89 GB
M5 · 32 GB	Q2_K	Too big	89 GB
M5 Pro · 24 GB	Q2_K	Too big	89 GB
M5 Pro · 48 GB	Q2_K	Too big	89 GB
M5 Pro · 64 GB	Q2_K	Too big	89 GB
M5 Max · 36 GB	Q2_K	Too big	89 GB
M5 Max · 48 GB	Q2_K	Too big	89 GB
M5 Max · 64 GB	Q2_K	Too big	89 GB
M5 Max · 128 GB	UD-Q2_K_XL	Runs well	92 GB	15
M5 Ultra · 96 GB	Q2_K	Too big	89 GB
M5 Ultra · 256 GB	Q5_K_M	Runs great	171 GB	19
M5 Ultra · 512 GB	Q8_0	Runs great	254 GB	17
M4 · 16 GB	Q2_K	Too big	89 GB
M4 · 24 GB	Q2_K	Too big	89 GB
M4 · 32 GB	Q2_K	Too big	89 GB
M4 Pro · 24 GB	Q2_K	Too big	89 GB
M4 Pro · 48 GB	Q2_K	Too big	89 GB
M4 Pro · 64 GB	Q2_K	Too big	89 GB
M4 Max · 36 GB	Q2_K	Too big	89 GB
M4 Max · 48 GB	Q2_K	Too big	89 GB
M4 Max · 64 GB	Q2_K	Too big	89 GB
M4 Max · 96 GB	Q2_K	Too big	89 GB
M4 Max · 128 GB	UD-Q2_K_XL	Runs well	92 GB	10
M3 · 8 GB	Q2_K	Too big	89 GB
M3 · 16 GB	Q2_K	Too big	89 GB
M3 · 24 GB	Q2_K	Too big	89 GB
M3 Pro · 18 GB	Q2_K	Too big	89 GB
M3 Pro · 36 GB	Q2_K	Too big	89 GB
M3 Max · 36 GB	Q2_K	Too big	89 GB
M3 Max · 48 GB	Q2_K	Too big	89 GB
M3 Max · 64 GB	Q2_K	Too big	89 GB
M3 Max · 96 GB	Q2_K	Too big	89 GB
M3 Max · 128 GB	UD-Q2_K_XL	Runs well	92 GB	8.8
M3 Ultra · 96 GB	Q2_K	Too big	89 GB
M3 Ultra · 256 GB	Q5_K_M	Runs great	171 GB	11
M3 Ultra · 512 GB	Q8_0	Runs great	254 GB	9.8
M2 · 8 GB	Q2_K	Too big	89 GB
M2 · 16 GB	Q2_K	Too big	89 GB
M2 · 24 GB	Q2_K	Too big	89 GB
M2 Pro · 16 GB	Q2_K	Too big	89 GB
M2 Pro · 32 GB	Q2_K	Too big	89 GB
M2 Max · 32 GB	Q2_K	Too big	89 GB
M2 Max · 64 GB	Q2_K	Too big	89 GB
M2 Max · 96 GB	Q2_K	Too big	89 GB
M2 Ultra · 64 GB	Q2_K	Too big	89 GB
M2 Ultra · 128 GB	UD-Q2_K_XL	Runs well	92 GB	14
M2 Ultra · 192 GB	IQ4_XS	Runs great	129 GB	12
M1 · 8 GB	Q2_K	Too big	89 GB
M1 · 16 GB	Q2_K	Too big	89 GB
M1 Pro · 16 GB	Q2_K	Too big	89 GB
M1 Pro · 32 GB	Q2_K	Too big	89 GB
M1 Max · 32 GB	Q2_K	Too big	89 GB
M1 Max · 64 GB	Q2_K	Too big	89 GB
M1 Ultra · 64 GB	Q2_K	Too big	89 GB
M1 Ultra · 128 GB	UD-Q2_K_XL	Runs well	92 GB	11

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Packaged by

2 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.

Information

Maker: Alibaba Qwen
Released: April 2025
Parameters: 235B, 22B active
Longest chat: 40K tokens
Reads pictures: No
Licence: apache-2.0
Downloads this month: 18,218
Likes: 95
Sizes: 5, 142 to 250 GB
Kind: Maker's release
Source: Qwen/Qwen3-235B-A22B

Badge for the model card

Shows on Qwen3 235B A22B's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.