Hugging FaceA community version of another maker's model.
- Rating
- 4.3
- Downloads
- 8.9K
- Likes
- 152
- Parameters
- 357B, 34B active
- Context
- 198K
- Licence
- mit
Too big for this Mac
Its smallest size needs 113 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.3 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 4.6 runs well from a Mac with an M1 Ultra and 128 GB of memory. 10 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.
- Ornith 1.0 397Bornith-ai · 3.5K downloadsToo big for this Mac · 113 GB
- Trinity Large PreviewArcee · 1.3K downloads · Arena 1379Too big for this Mac · 145 GB
- Ornith 1.5 397Bornith-ai · 1.3M downloadsToo big for this Mac · 82 GB
- Qwen3.5 397BAlibaba Qwen · 36K downloads · Arena 1441Too big for this Mac · 89 GB
Sizes
From unsloth/GLM-4.6-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 | 84 GB | 86 GBestimated | Open |
| UD-IQ1_S | 97 GB | 99 GBestimated | Open |
| UD-IQ1_M | 107 GB | 109 GBestimated | Open |
| UD-IQ2_XXS | 115 GB | 117 GBestimated | Open |
| UD-IQ2_M | 122 GB | 124 GBestimated | Open |
| Q2_K | 131 GB | 133 GBestimated | Open |
| Q2_K_L | 131 GB | 133 GBestimated | Open |
| UD-Q2_K_XL | 135 GB | 137 GBestimated | Open |
| UD-IQ3_XXS | 145 GB | 147 GBestimated | Open |
| Q3_K_S | 154 GB | 156 GBestimated | Open |
| UD-Q3_K_XL | 158 GB | 160 GBestimated | Open |
| Q3_K_M | 171 GB | 173 GBestimated | Open |
| IQ4_XS | 191 GB | 193 GBestimated | Open |
| IQ4_NL | 202 GB | 203 GBestimated | Open |
| Q4_0 | 202 GB | 204 GBestimated | Open |
| Q4_K_S | 203 GB | 205 GBestimated | Open |
| UD-Q4_K_XL | 204 GB | 206 GBestimated | Open |
| Q4_K_M | 216 GB | 217 GBestimated | Open |
| Q4_1 | 224 GB | 226 GBestimated | Open |
| Q5_K_S | 246 GB | 248 GBestimated | Open |
| UD-Q5_K_XL | 252 GB | 254 GBestimated | Open |
| Q5_K_M | 253 GB | 255 GBestimated | Open |
| Q6_K | 293 GB | 295 GBestimated | Open |
| UD-Q6_K_XL | 299 GB | 301 GBestimated | Open |
| Q8_0 | 379 GB | 381 GBestimated | Open |
| UD-Q8_K_XL | 390 GB | 392 GBestimated | Open |
| BF16 | 714 GB | 716 GBestimated | Open |
Run It Anywhere
GLM 4.6 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-4.6-GGUF:UD-TQ1_0 - llama.cppMac, Windows, Linux
llama-server -hf unsloth/GLM-4.6-GGUF:UD-TQ1_0 - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/GLM-4.6-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 124 GB | |
| 8 GB | None worth running | needs 124 GB | |
| 10 GB | None worth running | needs 124 GB | |
| 11 GB | None worth running | needs 124 GB | |
| 12 GB | None worth running | needs 124 GB | |
| 16 GB | None worth running | needs 124 GB | |
| 20 GB | None worth running | needs 124 GB | |
| 24 GB | None worth running | needs 124 GB | |
| 32 GB | None worth running | needs 124 GB | |
| 48 GB | None worth running | needs 124 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 | 113 GB | |
| M6 · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M6 · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Pro · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Pro · 48 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Pro · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Max · 36 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Max · 48 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Max · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Max · 128 GB | UD-IQ1_S | Runs well | 101 GB | 11 |
| M5 Ultra · 96 GB | UD-TQ1_0 | Too big | 113 GB | |
| M5 Ultra · 256 GB | IQ4_NL | Runs well | 203 GB | 14 |
| M5 Ultra · 512 GB | UD-Q6_K_XL | Runs great | 328 GB | 11 |
| M4 · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Pro · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Pro · 48 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Pro · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Max · 36 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Max · 48 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Max · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Max · 96 GB | UD-TQ1_0 | Too big | 113 GB | |
| M4 Max · 128 GB | UD-IQ1_S | Runs well | 101 GB | 7.9 |
| M3 · 8 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Pro · 18 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Pro · 36 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Max · 36 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Max · 48 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Max · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Max · 96 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Max · 128 GB | UD-IQ1_S | Runs well | 101 GB | 6.4 |
| M3 Ultra · 96 GB | UD-TQ1_0 | Too big | 113 GB | |
| M3 Ultra · 256 GB | IQ4_NL | Runs well | 203 GB | 8.3 |
| M3 Ultra · 512 GB | UD-Q6_K_XL | Runs great | 328 GB | 6.7 |
| M2 · 8 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 · 24 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Pro · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Pro · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Max · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Max · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Max · 96 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Ultra · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M2 Ultra · 128 GB | UD-IQ1_S | Runs well | 101 GB | 11 |
| M2 Ultra · 192 GB | UD-IQ3_XXS | Runs well | 152 GB | 9.5 |
| M1 · 8 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Pro · 16 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Pro · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Max · 32 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Max · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Ultra · 64 GB | UD-TQ1_0 | Too big | 113 GB | |
| M1 Ultra · 128 GB | UD-IQ1_S | Runs well | 101 GB | 9.2 |
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
- September 2025
- Parameters
- 357B, 34B active
- Longest chat
- 198K tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 8,876
- Likes
- 152
- Sizes
- 27, 84 to 714 GB
- Kind
- Community version
- Source
- zai-org/GLM-4.6
Badge for the model card
Shows on GLM 4.6'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.