Hugging FaceA community version of another maker's model that reads pictures as well as text.
- Rating
- 4.9
- Downloads
- 960K
- Likes
- 646
- Parameters
- 321B, 25B active
- Context
- 1M
- Licence
- mit
Too big for this Mac
Its smallest size needs 89 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.
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 5.3 Flash 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.
Sizes
From unsloth/GLM-5.3-Flash-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-IQ1_S | 93 GB | 93 GBestimated | Open |
| UD-IQ1_M | 98 GB | 98 GBestimated | Open |
| UD-IQ2_XXS | 102 GB | 102 GBestimated | Open |
| UD-Q2_K_XL | 109 GB | 109 GBestimated | Open |
| UD-IQ3_XXS | 120 GB | 121 GBestimated | Open |
| UD-Q3_K_XL | 148 GB | 148 GBestimated | Open |
| UD-IQ4_XS | 157 GB | 157 GBestimated | Open |
| UD-Q4_K_XL | 200 GB | 200 GBestimated | Open |
| UD-Q5_K_XL | 240 GB | 240 GBestimated | Open |
| UD-Q6_K_XL | 292 GB | 292 GBestimated | Open |
| Q8_0 | 341 GB | 341 GBestimated | Open |
| BF16 | 642 GB | 642 GBestimated | Open |
Run It Anywhere
GLM 5.3 Flash 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, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/unsloth/GLM-5.3-Flash-GGUF:UD-IQ1_S - llama.cppMac, Windows, Linux
llama-server -hf unsloth/GLM-5.3-Flash-GGUF:UD-IQ1_S - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/GLM-5.3-Flash-GGUF:UD-IQ1_S
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 109 GB | |
| 8 GB | None worth running | needs 109 GB | |
| 10 GB | None worth running | needs 109 GB | |
| 11 GB | None worth running | needs 109 GB | |
| 12 GB | None worth running | needs 109 GB | |
| 16 GB | None worth running | needs 109 GB | |
| 20 GB | None worth running | needs 109 GB | |
| 24 GB | None worth running | needs 109 GB | |
| 32 GB | None worth running | needs 109 GB | |
| 48 GB | None worth running | needs 109 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 | IQ2_XXS | Too big | 89 GB | |
| M6 · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M6 · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M5 · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M5 · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M5 · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Pro · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Pro · 48 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Pro · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Max · 36 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Max · 48 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Max · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Max · 128 GB | UD-IQ1_M | Runs well | 99 GB | 28 |
| M5 Ultra · 96 GB | IQ2_XXS | Too big | 89 GB | |
| M5 Ultra · 256 GB | UD-IQ4_XS | Runs great | 164 GB | 34 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 348 GB | 20 |
| M4 · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M4 · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M4 · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Pro · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Pro · 48 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Pro · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Max · 36 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Max · 48 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Max · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Max · 96 GB | IQ2_XXS | Too big | 89 GB | |
| M4 Max · 128 GB | UD-IQ1_M | Runs well | 99 GB | 20 |
| M3 · 8 GB | IQ2_XXS | Too big | 89 GB | |
| M3 · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M3 · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Pro · 18 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Pro · 36 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Max · 36 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Max · 48 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Max · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Max · 96 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Max · 128 GB | UD-IQ1_M | Runs well | 99 GB | 17 |
| M3 Ultra · 96 GB | IQ2_XXS | Too big | 89 GB | |
| M3 Ultra · 256 GB | UD-IQ4_XS | Runs great | 164 GB | 20 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 348 GB | 12 |
| M2 · 8 GB | IQ2_XXS | Too big | 89 GB | |
| M2 · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M2 · 24 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Pro · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Pro · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Max · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Max · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Max · 96 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Ultra · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M2 Ultra · 128 GB | UD-IQ1_M | Runs well | 99 GB | 27 |
| M2 Ultra · 192 GB | UD-IQ3_XXS | Runs great | 127 GB | 24 |
| M1 · 8 GB | IQ2_XXS | Too big | 89 GB | |
| M1 · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Pro · 16 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Pro · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Max · 32 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Max · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Ultra · 64 GB | IQ2_XXS | Too big | 89 GB | |
| M1 Ultra · 128 GB | UD-IQ1_M | Runs well | 99 GB | 22 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
9 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- Z.ai
- Released
- August 2026
- Parameters
- 321B, 25B active
- Longest chat
- 1M tokens
- Reads pictures
- Yes
- Licence
- mit
- Downloads this month
- 959,524
- Likes
- 646
- Sizes
- 12, 93 to 642 GB
- Kind
- Community version
- Source
- zai-org/GLM-5.3-Flash
Badge for the model card
Shows on GLM 5.3 Flash'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.