Nanbeige4.1 3B 8bit is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 4.2GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.25.
| LLM Name | Nanbeige4.1 3B 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Nanbeige4.1-3B-8bit |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 4.2 GB |
| Updated | 2026-05-25 |
| Maintainer | mlx-community |
| Model Type | llama |
| Model Files | |
| Supported Languages | en zh |
| Quantization Type | 8bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <unk> |
| Vocabulary Size | 166144 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanbeige4.1 3B Heretic 8bit | 256K / 4.2 GB | 45 | 2 |
| Llama 3.2 3B Legal SFT | 128K / 6.5 GB | 41 | 0 |
| Llama3.2 3B Base Math | 128K / 6.5 GB | 559 | 0 |
| Llama3.2 3B INST Math1 | 128K / 6.5 GB | 44 | 0 |
| Llama3 2 3B Indonesian Sft | 128K / 2.2 GB | 19 | 0 |
| Llama3.2 3B Base Code | 128K / 6.5 GB | 49 | 0 |
| Llama32 3B En Emo 2000 Stp | 128K / 2.2 GB | 10 | 1 |
| Llama32 3B En Emo 300 Stp | 128K / 2.2 GB | 9 | 0 |
| Llama32 3B En Emo 1000 Stp | 128K / 2.2 GB | 5 | 0 |
| Llama32 3B En Emo 5000 Stp | 128K / 2.2 GB | 9 | 0 |
🆘 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! 🌟