unsloth
GLM 5.3
GLM 5.3 is a 753.9B mixture-of-experts glm-dsa model from unsloth, with about 136.6B parameters active per token. Configured context length is 1,048,576 tokens. License: other. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters754B / 137B active
Context1024K
Attentionmla
Licenseother
78 layers · 64 KV heads · head dim 192 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 1404.4 GB | Hugging Face file bytes |
| Q8_0 | 746.3 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 637.4 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 523.8 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 435.2 GB | Hugging Face file bytes |
| UD-IQ4_XS | 340.2 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 319.4 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 262.3 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 236.4 GB | Hugging Face file bytes |
| UD-IQ1_M | 212.8 GB | Hugging Face file bytes |
| UD-IQ1_S | 201.8 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 3060 12GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4060 Ti 16GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4090 | Won't fit | UD-IQ1_S | — |
| GeForce RTX 5090 | Won't fit | UD-IQ1_S | — |
| Apple M4 Pro | Won't fit | UD-IQ1_S | — |
| Apple M5 | Won't fit | UD-IQ1_S | — |
| CPU only · DDR5-5600 | Won't fit | UD-IQ1_S | — |
Smallest devices that fit it fully
No GPU or Mac in the catalog fits this model inside the default memory budget. A partial offload or a larger machine is required.
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (UD-IQ1_S).
llama.cpp
llama-server -hf unsloth/GLM-5.3-GGUF:UD-IQ1_S -c 2048 -ngl 0
Ollama
ollama run glm-5.3
LM Studio
lms get unsloth/GLM-5.3-GGUF # Then load quant UD-IQ1_S