Arxiv:2402.17764 Autotrain compatible Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/1bitLLM/bitnet_b1_58-3B
Bitnet B1 58 3B 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)
Bitnet B1 58 3B Parameters and Internals
| Additional Notes |
| ||||||||||||
| Training Details |
|
| LLM Name | Bitnet B1 58 3B |
| Repository 🤗 | https://huggingface.co/1bitLLM/bitnet_b1_58-3B |
| Model Size | 3b |
| Required VRAM | 13.3 GB |
| Updated | 2025-09-23 |
| Maintainer | 1bitLLM |
| Model Type | llama |
| Model Files | |
| Model Architecture | BitnetForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.39.0 |
| Tokenizer Class | BitnetTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to Bitnet B1 58 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bitnet 5B V1 | 2K / 9.2 GB | 11 | 1 |
| Bitnet B1 58 3B Coder | 2K / 6.6 GB | 6 | 1 |
| Bitnet B1 58 3B Quantized | 2K / 1.1 GB | 8 | 12 |
| Bitnet B1 58 Large Q8 0 Gguf | 2K / 0.8 GB | 44 | 0 |
Rank the Bitnet B1 58 3B 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? 51560 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124