unsloth / text-generation Open weights updated 10 months ago

GLM-4.5-Air-GGUF

Name: GLM-4.5-Air-GGUF
Author: unsloth

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Params

110.5 B

Context

131,072

Downloads 30d

144 K

Likes

190

Commercial use: allowed mit Not gated GGUF 2 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (3 recorded)

144 K downloads in the last 30 days

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-4.5-Air-UD-IQ1_S.gguf	IQ1_S	38.5 GB	59.4 GB	❌ Won’t fit
GLM-4.5-Air-UD-IQ1_M.gguf	IQ1_M	40.1 GB	61.1 GB	❌ Won’t fit
GLM-4.5-Air-UD-IQ2_XXS.gguf	IQ2_XXS	42.7 GB	64.0 GB	❌ Won’t fit
GLM-4.5-Air-UD-IQ2_M.gguf	IQ2_M	44.4 GB	65.9 GB	❌ Won’t fit
GLM-4.5-Air-Q2_K.gguf	Q2_K	45.3 GB	66.9 GB	❌ Won’t fit
GLM-4.5-Air-Q2_K_L.gguf	Q2_K_L	45.5 GB	67.1 GB	❌ Won’t fit
GLM-4.5-Air-UD-Q2_K_XL.gguf	Q2_K_XL	47.4 GB	69.3 GB	❌ Won’t fit
GLM-4.5-Air-BF16-00001-of-00005.gguf	GGUF	49.8 GB	71.9 GB	❌ Won’t fit

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

copy-paste, exact tags checked against the Hub

~ · ollama · GGUF

$ ollama run glm-4-5-air-gguf

# pin the quantization explicitly
$ ollama run glm-4-5-air-gguf-gguf

est. VRAM 71.9 GBon RTX 4090 · 24 GBJSON API →

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

Compare with any text-generation model

Popular comparisons