unsloth / text-generation updated 3 weeks ago

GLM-5.3-GGUF

Name: GLM-5.3-GGUF
Author: unsloth

See Unsloth Dynamic 3.0 GGUFs for our quantization benchmarks. You can now run GLM-5.3 in Unsloth Desktop with toggles for Low, High and Max thinking. Read our GLM-5.3 guide for analysis and instructions.

Params

—

Context

—

Downloads 30d

492 K

Likes

Licence: other Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 15 days

492 K200 K

Sep 6Sep 11Sep 16Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
GLM-5.3-BF16-00005-of-00033.gguf	GGUF	46.8 GB	52.0 GB	❌ Won’t fit
GLM-5.3-UD-IQ2_M-00002-of-00006.gguf	IQ2_M	49.2 GB	54.6 GB	❌ Won’t fit
GLM-5.3-Q8_0-00003-of-00017.gguf	Q8	49.3 GB	54.7 GB	❌ Won’t fit
GLM-5.3-UD-IQ1_M-00005-of-00006.gguf	IQ1_M	49.7 GB	55.2 GB	❌ Won’t fit
GLM-5.3-UD-IQ4_XS-00005-of-00009.gguf	IQ4_XS	49.9 GB	55.4 GB	❌ Won’t fit
GLM-5.3-UD-IQ1_S-00002-of-00006.gguf	IQ1_S	50.0 GB	55.5 GB	❌ Won’t fit
GLM-5.3-UD-IQ3_XXS-00002-of-00007.gguf	IQ3_XXS	50.0 GB	55.5 GB	❌ Won’t fit
GLM-5.3-UD-Q2_K_XL-00006-of-00007.gguf	Q2_K_XL	50.0 GB	55.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · ollama · GGUF

$ ollama run glm-5-3-gguf

# pin the quantization explicitly
$ ollama run glm-5-3-gguf-gguf

est. VRAM 52.0 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence: other
First seen on the Hub: 2026-08-28
Base model: GLM-5.3
Training datasets: undisclosed
Added to our catalog: 2026-09-06

Family

Base model and the most-downloaded derivatives in the catalog.

Base GLM-5.3 zai-org 947 K

Compare with any text-generation model