Model Card on HF 🤗: https://huggingface.co/amd/Instella-3B
Instella 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)
Instella 3B Parameters and Internals
| LLM Name | Instella 3B |
| Repository 🤗 | https://huggingface.co/amd/Instella-3B |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-07-02 |
| Maintainer | amd |
| Model Type | instella |
| Model Files | |
| Model Architecture | InstellaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.48.0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | <|padding|> |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
Best Alternatives to Instella 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Instella 3B Instruct | 4K / 6.2 GB | 989 | 50 |
| Instella 3B Stage1 | 4K / 6.2 GB | 59 | 13 |
| Instella 3B SFT | 4K / 6.2 GB | 78 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than amd/Instella-3B .
Rank the Instella 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124