Llava Phi 2 3B is an open-source language model by marianna13. Features: 3b LLM, VRAM: 11.2GB, Context: 2K, License: mit, Instruction-Based, LLM Explorer Score: 0.11.
Arxiv:2401.02330 Custom code Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr... En Endpoints compatible Instruct Phi-llava Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/marianna13/llava-phi-2-3b
Llava Phi 2 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)
Llava Phi 2 3B Parameters and Internals
| Model Type |
|
| LLM Name | Llava Phi 2 3B |
| Repository 🤗 | https://huggingface.co/marianna13/llava-phi-2-3b |
| Model Size | 3b |
| Required VRAM | 11.2 GB |
| Updated | 2026-05-22 |
| Maintainer | marianna13 |
| Model Type | phi-llava |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlavaPhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 51200 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Llava Phi 2 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava Phi 2 3B Siglip | 2K / 11.2 GB | 25 | 3 |
| Llava Phi2 | 2K / 12.3 GB | 42 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than marianna13/llava-phi-2-3b .
Rank the Llava Phi 2 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? 53999 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