Qwen2.5 Omni 3B is an open-source language model by Qwen. Features: 3b LLM, VRAM: 12GB, License: other, LLM Explorer Score: 0.33.
Arxiv:2503.20215 Any-to-any En Endpoints compatible Multimodal Qwen2 5 omni Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-Omni-3B
Qwen2.5 Omni 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)
Qwen2.5 Omni 3B Parameters and Internals
| LLM Name | Qwen2.5 Omni 3B |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen2.5-Omni-3B |
| Model Size | 3b |
| Required VRAM | 12 GB |
| Updated | 2026-05-05 |
| Maintainer | Qwen |
| Model Type | qwen2_5_omni |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2_5OmniModel |
| License | other |
| Model Max Length | 32768 |
| Transformers Version | 4.51.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the Qwen2.5 Omni 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? 53620 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