Skip to content

GLM-4.5-Air-8bit

mlx-community/GLM-4.5-Air-8bit
8-bit Open on Hugging Face
Parameters
107B
Weights (est.)
≈ 114 GB
Mac memory (est.)
192 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Run it

With mlx-lm on an Apple silicon Mac:

pip install mlx-lmmlx_lm.generate --model mlx-community/GLM-4.5-Air-8bit --prompt "Hello"

Details

Base model
zai-org/GLM-4.5-Air (quantized)
Vendor
zai-org
Task
Text generation
Quantisation
8-bit
Licence
mit
Downloads
535 in the last 30 days · 95K all time · 11 likes
Published
2025-07-28 · updated 2025-07-29 (1y ago)
Languages
en, zh
Tags
glm4_moe

Other MLX builds of zai-org/GLM-4.5-Air

Build Quantisation Weights Mac memory Downloads
GLM-4.5-Air-2bit-DWQ 2-bit DWQ ≈ 33.4 GB 48 GB+ 52
GLM-4.5-Air-2bit 2-bit ≈ 33.4 GB 48 GB+ 62
GLM-4.5-Air-3bit-DWQ-v2 3-bit DWQ ≈ 46.8 GB 64 GB+ 75
GLM-4.5-Air-3bit-DWQ 3-bit DWQ ≈ 46.8 GB 64 GB+ 59
GLM-4.5-Air-3bit 3-bit ≈ 46.8 GB 64 GB+ 501
GLM-4.5-Air-4bit 4-bit ≈ 60.1 GB 96 GB+ 793
GLM-4.5-Air-nvfp4 4-bit ≈ 60.1 GB 96 GB+ 57
GLM-4.5-Air-mxfp4 MXFP4 ≈ 60.1 GB 96 GB+ 54
GLM-4.5-Air-5bit 5-bit ≈ 73.5 GB 96 GB+ 54
GLM-4.5-Air-6bit 6-bit ≈ 86.8 GB 128 GB+ 68
GLM-4.5-Air-8bit (this one) 8-bit ≈ 114 GB 192 GB+ 535
GLM-4.5-Air-mxfp8 MXFP8 ≈ 114 GB 192 GB+ 74
GLM-4.5-Air-bf16 bf16 ≈ 214 GB 256 GB+ 322