Outmake Models
Models

GLM 5.2

Z.ai · June 2026

Get Hugging Face

A community version of another maker's model.

Rating
4.9
Downloads
73K
Likes
648
Parameters
754B, 42B active
Context
1M
Licence
mit

Too big for this Mac

Its smallest size needs 272 GB of memory, more than M4 · 16 GB can give it.

Ratings

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

Text
1475
Coding
1514

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.

GLM 5.2 runs well from a Mac with an M3 Ultra and 512 GB of memory. 2 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 unsloth/GLM-5.2-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ1_S217 GB217 GBestimatedOpen
UD-IQ1_M228 GB229 GBestimatedOpen
UD-IQ2_XXS238 GB239 GBestimatedOpen
UD-IQ2_M239 GB239 GBestimatedOpen
UD-Q2_K_XL254 GB254 GBestimatedOpen
UD-IQ3_XXS282 GB282 GBestimatedOpen
UD-IQ3_S309 GB309 GBestimatedOpen
UD-Q3_K_M343 GB343 GBestimatedOpen
UD-Q3_K_XL343 GB344 GBestimatedOpen
UD-IQ4_XS365 GB366 GBestimatedOpen
UD-IQ4_NL373 GB373 GBestimatedOpen
UD-Q4_K_S436 GB437 GBestimatedOpen
UD-Q4_K_M466 GB466 GBestimatedOpen
UD-Q4_K_XL467 GB468 GBestimatedOpen
UD-Q5_K_S527 GB528 GBestimatedOpen
UD-Q5_K_M561 GB561 GBestimatedOpen
UD-Q5_K_XL562 GB563 GBestimatedOpen
UD-Q6_K626 GB626 GBestimatedOpen
UD-Q6_K_XL684 GB685 GBestimatedOpen
Q8_0801 GB802 GBestimatedOpen
UD-Q8_K_XL820 GB820 GBestimatedOpen
BF161508 GB1509 GBestimatedOpen

Run It Anywhere

GLM 5.2 is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_S size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/GLM-5.2-GGUF:UD-IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/GLM-5.2-GGUF:UD-IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/GLM-5.2-GGUF:UD-IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 239 GB
8 GBNone worth runningneeds 239 GB
10 GBNone worth runningneeds 239 GB
11 GBNone worth runningneeds 239 GB
12 GBNone worth runningneeds 239 GB
16 GBNone worth runningneeds 239 GB
20 GBNone worth runningneeds 239 GB
24 GBNone worth runningneeds 239 GB
32 GBNone worth runningneeds 239 GB
48 GBNone worth runningneeds 239 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-IQ1_SToo big272 GB
M6 · 24 GBUD-IQ1_SToo big272 GB
M6 · 32 GBUD-IQ1_SToo big272 GB
M5 · 16 GBUD-IQ1_SToo big272 GB
M5 · 24 GBUD-IQ1_SToo big272 GB
M5 · 32 GBUD-IQ1_SToo big272 GB
M5 Pro · 24 GBUD-IQ1_SToo big272 GB
M5 Pro · 48 GBUD-IQ1_SToo big272 GB
M5 Pro · 64 GBUD-IQ1_SToo big272 GB
M5 Max · 36 GBUD-IQ1_SToo big272 GB
M5 Max · 48 GBUD-IQ1_SToo big272 GB
M5 Max · 64 GBUD-IQ1_SToo big272 GB
M5 Max · 128 GBUD-IQ1_SToo big272 GB
M5 Ultra · 96 GBUD-IQ1_SToo big272 GB
M5 Ultra · 256 GBUD-IQ1_SToo big272 GB
M5 Ultra · 512 GBUD-IQ4_NLRuns well400 GB18
M4 · 16 GBUD-IQ1_SToo big272 GB
M4 · 24 GBUD-IQ1_SToo big272 GB
M4 · 32 GBUD-IQ1_SToo big272 GB
M4 Pro · 24 GBUD-IQ1_SToo big272 GB
M4 Pro · 48 GBUD-IQ1_SToo big272 GB
M4 Pro · 64 GBUD-IQ1_SToo big272 GB
M4 Max · 36 GBUD-IQ1_SToo big272 GB
M4 Max · 48 GBUD-IQ1_SToo big272 GB
M4 Max · 64 GBUD-IQ1_SToo big272 GB
M4 Max · 96 GBUD-IQ1_SToo big272 GB
M4 Max · 128 GBUD-IQ1_SToo big272 GB
M3 · 8 GBUD-IQ1_SToo big272 GB
M3 · 16 GBUD-IQ1_SToo big272 GB
M3 · 24 GBUD-IQ1_SToo big272 GB
M3 Pro · 18 GBUD-IQ1_SToo big272 GB
M3 Pro · 36 GBUD-IQ1_SToo big272 GB
M3 Max · 36 GBUD-IQ1_SToo big272 GB
M3 Max · 48 GBUD-IQ1_SToo big272 GB
M3 Max · 64 GBUD-IQ1_SToo big272 GB
M3 Max · 96 GBUD-IQ1_SToo big272 GB
M3 Max · 128 GBUD-IQ1_SToo big272 GB
M3 Ultra · 96 GBUD-IQ1_SToo big272 GB
M3 Ultra · 256 GBUD-IQ1_SToo big272 GB
M3 Ultra · 512 GBUD-IQ4_NLRuns well400 GB11
M2 · 8 GBUD-IQ1_SToo big272 GB
M2 · 16 GBUD-IQ1_SToo big272 GB
M2 · 24 GBUD-IQ1_SToo big272 GB
M2 Pro · 16 GBUD-IQ1_SToo big272 GB
M2 Pro · 32 GBUD-IQ1_SToo big272 GB
M2 Max · 32 GBUD-IQ1_SToo big272 GB
M2 Max · 64 GBUD-IQ1_SToo big272 GB
M2 Max · 96 GBUD-IQ1_SToo big272 GB
M2 Ultra · 64 GBUD-IQ1_SToo big272 GB
M2 Ultra · 128 GBUD-IQ1_SToo big272 GB
M2 Ultra · 192 GBUD-IQ1_SToo big272 GB
M1 · 8 GBUD-IQ1_SToo big272 GB
M1 · 16 GBUD-IQ1_SToo big272 GB
M1 Pro · 16 GBUD-IQ1_SToo big272 GB
M1 Pro · 32 GBUD-IQ1_SToo big272 GB
M1 Max · 32 GBUD-IQ1_SToo big272 GB
M1 Max · 64 GBUD-IQ1_SToo big272 GB
M1 Ultra · 64 GBUD-IQ1_SToo big272 GB
M1 Ultra · 128 GBUD-IQ1_SToo big272 GB

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

Information

Maker
Z.ai
Released
June 2026
Parameters
754B, 42B active
Longest chat
1M tokens
Reads pictures
No
Licence
mit
Downloads this month
72,836
Likes
648
Sizes
22, 217 to 1508 GB
Kind
Community version

Badge for the model card

Shows on GLM 5.2'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