3-bit 3bit Base model:quantized:zai-org/g... Base model:zai-org/glm-4.5-air Conversational En Glm4 moe Mlx Quantized Region:us Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/GLM-4.5-Air-3bit
GLM 4.5 Air 3bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
GLM 4.5 Air 3bit Parameters and Internals
| LLM Name | GLM 4.5 Air 3bit |
| Repository 🤗 | https://huggingface.co/mlx-community/GLM-4.5-Air-3bit |
| Base Model(s) | |
| Model Size | 106.9b |
| Required VRAM | 46.6 GB |
| Updated | 2025-07-30 |
| Maintainer | mlx-community |
| Model Type | glm4_moe |
| Model Files | |
| Supported Languages | en zh |
| Quantization Type | 3bit |
| Model Architecture | Glm4MoeForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.54.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151552 |
| Torch Data Type | bfloat16 |
Best Alternatives to GLM 4.5 Air 3bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GLM 4.5 Air 4bit | 128K / 60.4 GB | 1461 | 14 |
| GLM 4.5 Air 2bit | 128K / 33.4 GB | 268 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/GLM-4.5-Air-3bit .
Rank the GLM 4.5 Air 3bit Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124