Outmake Models
Models

Qwen3 VL 235B A22B

Alibaba Qwen · September 2025

Get Hugging Face

A community version of another maker's model that reads pictures as well as text.

Rating
4.1
Downloads
9.7K
Likes
44
Parameters
235B, 22B active
Context
256K
Licence
apache-2.0

Too big for this Mac

Its smallest size needs 84 GB of memory, more than M4 · 16 GB can give it.

Ratings

4.1 out of 5, across people's blind votes on its answers.

Text
1413
Coding
1463
Vision
1228

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.

Qwen3 VL 235B A22B runs well from a Mac with an M2 Max and 96 GB of memory. 15 of 59 Mac configurations run it well. It is a re-tune or merge made by someone other than the original model's maker, so its ratings, where it has any, are its own.

Compare with

The nearest models in size.

Sizes

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

SizeDownloadMemory at 8KGet
Qwen3VL-235B-A22B-Instruct-Q4_K_M-split142 GB143 GBestimatedOpen
Q8_0250 GB251 GBestimatedOpen
Qwen3VL-235B-A22B-Instruct-F16-split470 GB471 GBestimatedOpen

Run It Anywhere

Qwen3 VL 235B A22B is an open model, so any app that runs GGUF files can run it. These take the Qwen3VL-235B-A22B-Instruct-Q4_K_M-split 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-VL-235B-A22B-Instruct-GGUF:Qwen3VL-235B-A22B-Instruct-Q4_K_M-split
  • llama.cppMac, Windows, Linuxllama-server -hf Qwen/Qwen3-VL-235B-A22B-Instruct-GGUF:Qwen3VL-235B-A22B-Instruct-Q4_K_M-split
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/Qwen/Qwen3-VL-235B-A22B-Instruct-GGUF:Qwen3VL-235B-A22B-Instruct-Q4_K_M-split
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 143 GB
8 GBNone worth runningneeds 143 GB
10 GBNone worth runningneeds 143 GB
11 GBNone worth runningneeds 143 GB
12 GBNone worth runningneeds 143 GB
16 GBNone worth runningneeds 143 GB
20 GBNone worth runningneeds 143 GB
24 GBNone worth runningneeds 143 GB
32 GBNone worth runningneeds 143 GB
48 GBNone worth runningneeds 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
MacSizeFitMemoryWrites
M6 · 16 GBUD-TQ1_0Too big84 GB
M6 · 24 GBUD-TQ1_0Too big84 GB
M6 · 32 GBUD-TQ1_0Too big84 GB
M5 · 16 GBUD-TQ1_0Too big84 GB
M5 · 24 GBUD-TQ1_0Too big84 GB
M5 · 32 GBUD-TQ1_0Too big84 GB
M5 Pro · 24 GBUD-TQ1_0Too big84 GB
M5 Pro · 48 GBUD-TQ1_0Too big84 GB
M5 Pro · 64 GBUD-TQ1_0Too big84 GB
M5 Max · 36 GBUD-TQ1_0Too big84 GB
M5 Max · 48 GBUD-TQ1_0Too big84 GB
M5 Max · 64 GBUD-TQ1_0Too big84 GB
M5 Max · 128 GBUD-IQ3_XXSRuns well98 GB15
M5 Ultra · 96 GBUD-IQ1_SRuns well67 GB31
M5 Ultra · 256 GBQ5_K_MRuns great174 GB19
M5 Ultra · 512 GBQ8_0Runs great279 GB17
M4 · 16 GBUD-TQ1_0Too big84 GB
M4 · 24 GBUD-TQ1_0Too big84 GB
M4 · 32 GBUD-TQ1_0Too big84 GB
M4 Pro · 24 GBUD-TQ1_0Too big84 GB
M4 Pro · 48 GBUD-TQ1_0Too big84 GB
M4 Pro · 64 GBUD-TQ1_0Too big84 GB
M4 Max · 36 GBUD-TQ1_0Too big84 GB
M4 Max · 48 GBUD-TQ1_0Too big84 GB
M4 Max · 64 GBUD-TQ1_0Too big84 GB
M4 Max · 96 GBUD-IQ1_SRuns well67 GB9.7
M4 Max · 128 GBUD-IQ3_XXSRuns well98 GB10
M3 · 8 GBUD-TQ1_0Too big84 GB
M3 · 16 GBUD-TQ1_0Too big84 GB
M3 · 24 GBUD-TQ1_0Too big84 GB
M3 Pro · 18 GBUD-TQ1_0Too big84 GB
M3 Pro · 36 GBUD-TQ1_0Too big84 GB
M3 Max · 36 GBUD-TQ1_0Too big84 GB
M3 Max · 48 GBUD-TQ1_0Too big84 GB
M3 Max · 64 GBUD-TQ1_0Too big84 GB
M3 Max · 96 GBUD-IQ1_SRuns well67 GB8.1
M3 Max · 128 GBUD-IQ3_XXSRuns well98 GB8.5
M3 Ultra · 96 GBUD-IQ1_SRuns well67 GB16
M3 Ultra · 256 GBQ5_K_MRuns great174 GB11
M3 Ultra · 512 GBQ8_0Runs great279 GB9.8
M2 · 8 GBUD-TQ1_0Too big84 GB
M2 · 16 GBUD-TQ1_0Too big84 GB
M2 · 24 GBUD-TQ1_0Too big84 GB
M2 Pro · 16 GBUD-TQ1_0Too big84 GB
M2 Pro · 32 GBUD-TQ1_0Too big84 GB
M2 Max · 32 GBUD-TQ1_0Too big84 GB
M2 Max · 64 GBUD-TQ1_0Too big84 GB
M2 Max · 96 GBUD-IQ1_SRuns well67 GB10
M2 Ultra · 64 GBUD-TQ1_0Too big84 GB
M2 Ultra · 128 GBUD-IQ3_XXSRuns well98 GB14
M2 Ultra · 192 GBIQ4_XSRuns great129 GB12
M1 · 8 GBUD-TQ1_0Too big84 GB
M1 · 16 GBUD-TQ1_0Too big84 GB
M1 Pro · 16 GBUD-TQ1_0Too big84 GB
M1 Pro · 32 GBUD-TQ1_0Too big84 GB
M1 Max · 32 GBUD-TQ1_0Too big84 GB
M1 Max · 64 GBUD-TQ1_0Too big84 GB
M1 Ultra · 64 GBUD-TQ1_0Too big84 GB
M1 Ultra · 128 GBUD-IQ3_XXSRuns well98 GB11

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
September 2025
Parameters
235B, 22B active
Longest chat
256K tokens
Reads pictures
Yes
Licence
apache-2.0
Downloads this month
9,655
Likes
44
Sizes
3, 142 to 470 GB
Kind
Community version

Badge for the model card

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

Runs on Mac badge

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.

Your Computer

Every model is judged for this Mac. Both are under About This Mac, in the Apple menu.

Every Mac · Every graphics card

Civitai

Open in OutmakeHugging Face

New to Outmake? Download the free beta