MoE LLaVA Phi2 Stage2 is an open-source language model by LanguageBind. Features: 3.1b LLM, VRAM: 6.2GB, Context: 2K, License: apache-2.0, MoE, LLM Explorer Score: 0.13.
Autotrain compatible Custom code Endpoints compatible Llava phi Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LanguageBind/MoE-LLaVA-Phi2-Stage2
MoE LLaVA Phi2 Stage2 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)
MoE LLaVA Phi2 Stage2 Parameters and Internals
| LLM Name | MoE LLaVA Phi2 Stage2 |
| Repository 🤗 | https://huggingface.co/LanguageBind/MoE-LLaVA-Phi2-Stage2 |
| Model Size | 3.1b |
| Required VRAM | 6.2 GB |
| Updated | 2025-09-23 |
| Maintainer | LanguageBind |
| Model Type | llava_phi |
| Model Files | |
| Model Architecture | LlavaPhiForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|extra_0|> |
| Vocabulary Size | 51200 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the MoE LLaVA Phi2 Stage2 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? 52473 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