Downloads · 30 days
102
2% of all-time downloads
GLM-4.5-Air-GGUF-IQ1_M
lovedheart/GLM-4.5-Air-GGUF-IQ1_M
GLM-4.5-Air-GGUF-IQ1_M is a machine learning model from lovedheart. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Use unsloth BF16 GGUF to quantize IQ1M/S. Blk.46 is not being used in llama.cpp therefore the weights of blk.46 are quantized to TQ10 to have minimum memory allocation.
All-time downloads
6.6K
Public
Repo size
434 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf378 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 5, 2025
- Updated
- Aug 26, 2025
- SHA
- dad9c6ab
Base models
Model card
From the Hugging Face model README
Use unsloth BF16 GGUF to quantize IQ1_M/S. Blk.46 is not being used in llama.cpp therefore the weights of blk.46 are quantized to TQ1_0 to have minimum memory allocation.
Added MXFP4 version:
- MXFP4: Embedding, Output are kept with Q6_K. The attn layers use IQ4_XS. All ffn expert layers including shared experts are quantized to SOTA MXFP4.
- MXFP4 Max: Embedding, Output and attn layers are kept with Q6_K. First layer uses full precision. The rest of ffn expert layers are quantized to SOTA MXFP4. The shared experts weights keep BF16.
- License
- mit
- Created
- Aug 5, 2025
- Updated
- Aug 26, 2025