Sarashina2.2 Vision 3B is an open-source language model by sbintuitions. Features: 3b LLM, VRAM: 7.6GB, License: mit, Instruction-Based, LLM Explorer Score: 0.26.
Arxiv:2007.00398 Arxiv:2104.12756 Arxiv:2403.19454 Arxiv:2404.07824 Arxiv:2410.17250 Base model:finetune:sbintuitio... Base model:sbintuitions/sarash... Custom code En Image-to-text Instruct Ja Multimodal Region:us Safetensors Sarashina2 vision Vision Vision-language
Model Card on HF 🤗: https://huggingface.co/sbintuitions/sarashina2.2-vision-3b
Sarashina2.2 Vision 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)
Sarashina2.2 Vision 3B Parameters and Internals
| LLM Name | Sarashina2.2 Vision 3B |
| Repository 🤗 | https://huggingface.co/sbintuitions/sarashina2.2-vision-3b |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 7.6 GB |
| Updated | 2026-04-21 |
| Maintainer | sbintuitions |
| Model Type | sarashina2_vision |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ja en |
| Model Architecture | Sarashina2VisionForCausalLM |
| License | mit |
| Model Max Length | 8192 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Rank the Sarashina2.2 Vision 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? 53053 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