GLM 4.5 Air 4bit is an open-source language model by mlx-community. Features: 106.9b LLM, VRAM: 60.4GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.21.
| LLM Name | GLM 4.5 Air 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/GLM-4.5-Air-4bit |
| Base Model(s) | |
| Model Size | 106.9b |
| Required VRAM | 60.4 GB |
| Updated | 2026-06-21 |
| Maintainer | mlx-community |
| Model Type | glm4_moe |
| Model Files | |
| Supported Languages | en zh |
| Quantization Type | 4bit |
| Model Architecture | Glm4MoeForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.54.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151552 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GLM 4.7 REAP 50 Mxfp4 | 198K / 98.4 GB | 1708 | 28 |
| GLM 4.7 | 198K / 335.4 GB | 492 | 9 |
| GLM 4.7 Int4 Mixed AutoRound | 198K / 193.5 GB | 266 | 25 |
| GLM 4.7 FP8 | 198K / 166.3 GB | 31 | 3 |
| GLM 4.5 Int4 Mixed AutoRound | 128K / 192.4 GB | 22 | 5 |
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟