Hugging FaceA community version of another maker's model.
- Rating
- 4.7
- Downloads
- 3.3K
- Likes
- 206
- Parameters
- 754B, 42B active
- Context
- 198K
- Licence
- mit
Too big for this Mac
Its smallest size needs 213 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.7 out of 5, across people's blind votes on its answers.
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 5.1 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-5.1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-IQ1_M | 206 GB | 206 GBestimated | Open |
| UD-IQ2_XXS | 221 GB | 221 GBestimated | Open |
| UD-IQ2_M | 236 GB | 237 GBestimated | Open |
| UD-Q2_K_XL | 252 GB | 253 GBestimated | Open |
| UD-IQ3_XXS | 268 GB | 269 GBestimated | Open |
| UD-IQ3_S | 280 GB | 280 GBestimated | Open |
| UD-Q3_K_S | 313 GB | 314 GBestimated | Open |
| UD-Q3_K_M | 338 GB | 339 GBestimated | Open |
| UD-Q3_K_XL | 340 GB | 341 GBestimated | Open |
| UD-IQ4_XS | 361 GB | 362 GBestimated | Open |
| UD-IQ4_NL | 369 GB | 369 GBestimated | Open |
| UD-Q4_K_S | 434 GB | 434 GBestimated | Open |
| MXFP4_MOE | 451 GB | 451 GBestimated | Open |
| UD-Q4_K_M | 465 GB | 465 GBestimated | Open |
| UD-Q4_K_XL | 466 GB | 467 GBestimated | Open |
| UD-Q5_K_S | 526 GB | 526 GBestimated | Open |
| UD-Q5_K_M | 558 GB | 559 GBestimated | Open |
| UD-Q5_K_XL | 560 GB | 561 GBestimated | Open |
| UD-Q6_K | 621 GB | 622 GBestimated | Open |
| UD-Q6_K_XL | 684 GB | 685 GBestimated | Open |
| Q8_0 | 801 GB | 802 GBestimated | Open |
| UD-Q8_K_XL | 811 GB | 811 GBestimated | Open |
| BF16 | 1508 GB | 1509 GBestimated | Open |
Run It Anywhere
GLM 5.1 is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_M size from unsloth straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/unsloth/GLM-5.1-GGUF:UD-IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf unsloth/GLM-5.1-GGUF:UD-IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/GLM-5.1-GGUF:UD-IQ1_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 237 GB | |
| 8 GB | None worth running | needs 237 GB | |
| 10 GB | None worth running | needs 237 GB | |
| 11 GB | None worth running | needs 237 GB | |
| 12 GB | None worth running | needs 237 GB | |
| 16 GB | None worth running | needs 237 GB | |
| 20 GB | None worth running | needs 237 GB | |
| 24 GB | None worth running | needs 237 GB | |
| 32 GB | None worth running | needs 237 GB | |
| 48 GB | None worth running | needs 237 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 | UD-IQ1_M | Too big | 213 GB | |
| M6 · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M6 · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Pro · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Pro · 48 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Pro · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Max · 36 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Max · 48 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Max · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Max · 128 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Ultra · 96 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Ultra · 256 GB | UD-IQ1_M | Too big | 213 GB | |
| M5 Ultra · 512 GB | UD-IQ4_NL | Runs well | 376 GB | 18 |
| M4 · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Pro · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Pro · 48 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Pro · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Max · 36 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Max · 48 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Max · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Max · 96 GB | UD-IQ1_M | Too big | 213 GB | |
| M4 Max · 128 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 · 8 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Pro · 18 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Pro · 36 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Max · 36 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Max · 48 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Max · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Max · 96 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Max · 128 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Ultra · 96 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Ultra · 256 GB | UD-IQ1_M | Too big | 213 GB | |
| M3 Ultra · 512 GB | UD-IQ4_NL | Runs well | 376 GB | 11 |
| M2 · 8 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 · 24 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Pro · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Pro · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Max · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Max · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Max · 96 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Ultra · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Ultra · 128 GB | UD-IQ1_M | Too big | 213 GB | |
| M2 Ultra · 192 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 · 8 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Pro · 16 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Pro · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Max · 32 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Max · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Ultra · 64 GB | UD-IQ1_M | Too big | 213 GB | |
| M1 Ultra · 128 GB | UD-IQ1_M | Too big | 213 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
- April 2026
- Parameters
- 754B, 42B active
- Longest chat
- 198K tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 3,288
- Likes
- 206
- Sizes
- 23, 206 to 1508 GB
- Kind
- Community version
- Source
- zai-org/GLM-5.1
Badge for the model card
Shows on GLM 5.1'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.