Arxiv:1910.09700 4-bit Autotrain compatible Conversational Custom code Endpoints compatible Gptq Phi3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/apry/best_4b
Best 4b 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)
Best 4B Parameters and Internals
| LLM Name | Best 4b |
| Repository 🤗 | https://huggingface.co/apry/best_4b |
| Model Size | 4b |
| Required VRAM | 2.3 GB |
| Updated | 2025-02-22 |
| Maintainer | apry |
| Model Type | phi3 |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Best 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Calme 2.1 Phi3.5 4B | 128K / 7.7 GB | 197 | 4 |
| Lunar 4B | 128K / 7.7 GB | 370 | 1 |
| Phi3.5 Gutenberg 4B | 128K / 7.7 GB | 188 | 4 |
| Calme 2.3 Phi3 4B | 4K / 7.7 GB | 5739 | 9 |
| Calme 2.1 Phi3 4B | 4K / 7.7 GB | 249 | 1 |
| Calme 2.2 Phi3 4B | 4K / 7.7 GB | 154 | 2 |
| Cream Phi 3 4B V1.1 | 4K / 7.7 GB | 168 | 1 |
| Cream Phi 3 4B V1 | 4K / 7.7 GB | 5 | 0 |
| Ruphi 4B | 128K / 7.6 GB | 71 | 0 |
| Phi 3.5 Mini Hyper | 128K / 7.7 GB | 50 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than apry/best_4b .
Rank the Best 4B 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227