π§
Qwen2.5 Vl 3b Instruct model by Qwen
β 42.4
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--qwen--qwen2.5-vl-3b-instruct
- slug
- qwen--qwen2.5-vl-3b-instruct
- source
- huggingface
- author
- Qwen
- license
- tags
- transformers, safetensors, qwen2_5_vl, image-to-text, multimodal, image-text-to-text, conversational, en, arxiv:2309.00071, arxiv:2409.12191, arxiv:2308.12966, text-generation-inference, endpoints_compatible, deploy:azure, region:us, eval-results
βοΈ Technical Specs
- architecture
- Qwen2_5_VLForConditionalGeneration
- params billions
- 3.75
- context length
- 32,768
- pipeline tag
- image-text-to-text
- vram gb
- 5.3
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 2GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 8,509,958
- stars
- 0
- forks
- 0
Data indexed from public sources. Updated daily.