Arxiv:2504.12285 8-bit Autotrain compatible Bitnet Chat Conversational Custom code En Endpoints compatible Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/microsoft/bitnet-b1.58-2B-4T
Bitnet B1.58 2B 4T 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 2B 4T Parameters and Internals
| LLM Name | Bitnet B1.58 2B 4T |
| Repository 🤗 | https://huggingface.co/microsoft/bitnet-b1.58-2B-4T |
| Model Size | 2b |
| Required VRAM | 1.2 GB |
| Updated | 2025-07-20 |
| Maintainer | microsoft |
| Model Type | bitnet |
| Model Files | |
| Supported Languages | en |
| Model Architecture | BitNetForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Bitnet B1.58 2B 4T
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bitnet B1.58 2B 4T Bf16 | 4K / 4.8 GB | 6692 | 33 |
| Bitnet DPO Merged Modelstock2 | 4K / 4.9 GB | 299 | 0 |
| Bitnet DPO Merged Ties | 4K / 4.8 GB | 217 | 1 |
| Bitnet DPO Merged Ties2 | 4K / 4.9 GB | 115 | 0 |
| Bitnet B1.58 Bifrost Sol 2B 4T | 4K / 4.8 GB | 6 | 1 |
Rank the Bitnet B1.58 2B 4T 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124