Hugging FaceA community version of another maker's model.
- Rating
- 4.6
- Downloads
- 11K
- Likes
- 228
- Parameters
- 754B, 42B active
- Context
- 198K
- Licence
- mit
Too big for this Mac
Its smallest size needs 183 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.6 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 runs well from a Mac with an M3 Ultra and 256 GB of memory. 4 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-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-TQ1_0 | 176 GB | 177 GBestimated | Open |
| UD-IQ1_S | 204 GB | 204 GBestimated | Open |
| UD-IQ1_M | 224 GB | 224 GBestimated | Open |
| UD-IQ2_XXS | 241 GB | 242 GBestimated | Open |
| UD-IQ2_M | 255 GB | 255 GBestimated | Open |
| Q2_K | 276 GB | 276 GBestimated | Open |
| Q2_K_L | 276 GB | 277 GBestimated | Open |
| UD-Q2_K_XL | 281 GB | 282 GBestimated | Open |
| UD-IQ3_XXS | 305 GB | 305 GBestimated | Open |
| Q3_K_S | 326 GB | 327 GBestimated | Open |
| UD-Q3_K_XL | 332 GB | 333 GBestimated | Open |
| Q3_K_M | 360 GB | 361 GBestimated | Open |
| IQ4_XS | 403 GB | 403 GBestimated | Open |
| MXFP4_MOE | 411 GB | 411 GBestimated | Open |
| IQ4_NL | 426 GB | 426 GBestimated | Open |
| Q4_0 | 427 GB | 428 GBestimated | Open |
| Q4_K_S | 428 GB | 429 GBestimated | Open |
| UD-Q4_K_XL | 431 GB | 431 GBestimated | Open |
| Q4_K_M | 456 GB | 456 GBestimated | Open |
| Q4_1 | 473 GB | 473 GBestimated | Open |
| Q5_K_S | 520 GB | 520 GBestimated | Open |
| Q5_K_M | 535 GB | 536 GBestimated | Open |
| UD-Q5_K_XL | 536 GB | 537 GBestimated | Open |
| Q6_K | 619 GB | 620 GBestimated | Open |
| UD-Q6_K_XL | 645 GB | 646 GBestimated | Open |
| Q8_0 | 801 GB | 802 GBestimated | Open |
| UD-Q8_K_XL | 869 GB | 869 GBestimated | Open |
| BF16 | 1508 GB | 1509 GBestimated | Open |
Run It Anywhere
GLM 5 is an open model, so any app that runs GGUF files can run it. These take the UD-TQ1_0 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-GGUF:UD-TQ1_0 - llama.cppMac, Windows, Linux
llama-server -hf unsloth/GLM-5-GGUF:UD-TQ1_0 - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/GLM-5-GGUF:UD-TQ1_0
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 255 GB | |
| 8 GB | None worth running | needs 255 GB | |
| 10 GB | None worth running | needs 255 GB | |
| 11 GB | None worth running | needs 255 GB | |
| 12 GB | None worth running | needs 255 GB | |
| 16 GB | None worth running | needs 255 GB | |
| 20 GB | None worth running | needs 255 GB | |
| 24 GB | None worth running | needs 255 GB | |
| 32 GB | None worth running | needs 255 GB | |
| 48 GB | None worth running | needs 255 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-TQ1_0 | Too big | 183 GB | |
| M6 · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M6 · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Pro · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Pro · 48 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Pro · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Max · 36 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Max · 48 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Max · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Max · 128 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Ultra · 96 GB | UD-TQ1_0 | Too big | 183 GB | |
| M5 Ultra · 256 GB | UD-TQ1_0 | Runs well | 183 GB | 30 |
| M5 Ultra · 512 GB | IQ4_XS | Runs well | 410 GB | 17 |
| M4 · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Pro · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Pro · 48 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Pro · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Max · 36 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Max · 48 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Max · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Max · 96 GB | UD-TQ1_0 | Too big | 183 GB | |
| M4 Max · 128 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 · 8 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Pro · 18 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Pro · 36 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Max · 36 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Max · 48 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Max · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Max · 96 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Max · 128 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Ultra · 96 GB | UD-TQ1_0 | Too big | 183 GB | |
| M3 Ultra · 256 GB | UD-TQ1_0 | Runs well | 183 GB | 16 |
| M3 Ultra · 512 GB | IQ4_XS | Runs well | 410 GB | 10 |
| M2 · 8 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 · 24 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Pro · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Pro · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Max · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Max · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Max · 96 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Ultra · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Ultra · 128 GB | UD-TQ1_0 | Too big | 183 GB | |
| M2 Ultra · 192 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 · 8 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Pro · 16 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Pro · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Max · 32 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Max · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Ultra · 64 GB | UD-TQ1_0 | Too big | 183 GB | |
| M1 Ultra · 128 GB | UD-TQ1_0 | Too big | 183 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
- February 2026
- Parameters
- 754B, 42B active
- Longest chat
- 198K tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 11,105
- Likes
- 228
- Sizes
- 28, 176 to 1508 GB
- Kind
- Community version
- Source
- zai-org/GLM-5
Badge for the model card
Shows on GLM 5'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.