Dayhoff 3B GR HM C is an open-source language model by microsoft. Features: 3b LLM, VRAM: 11.9GB, Context: 256K, License: mit.
Arxiv:2502.12479 Dataset:microsoft/dayhoff Deploy:azure Endpoints compatible Jamba Protein-generation Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/Dayhoff-3b-GR-HM-c
Dayhoff 3B GR HM C Parameters and Internals
| LLM Name | Dayhoff 3B GR HM C |
| Repository 🤗 | https://huggingface.co/microsoft/Dayhoff-3b-GR-HM-c |
| Model Size | 3b |
| Required VRAM | 11.9 GB |
| Updated | 2026-03-31 |
| Maintainer | microsoft |
| Model Type | jamba |
| Model Files | |
| Model Architecture | JambaForCausalLM |
| License | mit |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.42.4 |
| Tokenizer Class | ProteinTokenizer |
| Padding Token | ! |
| Vocabulary Size | 40 |
| Torch Data Type | float32 |
Best Alternatives to Dayhoff 3B GR HM C
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AI21 Jamba Reasoning 3B | 256K / 6.4 GB | 2949 | 133 |
| Dayhoff 3B GR HM 1000 | 256K / 6 GB | 41 | 2 |
| Dayhoff 3B GR HM 41000 | 256K / 6 GB | 56 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than microsoft/Dayhoff-3b-GR-HM-c .
Rank the Dayhoff 3B GR HM C 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? 52334 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a