Model Card on HF 🤗: https://huggingface.co/sbintuitions/sarashina2.2-3b
Sarashina2.2 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)
Sarashina2.2 3B Parameters and Internals
| LLM Name | Sarashina2.2 3B |
| Repository 🤗 | https://huggingface.co/sbintuitions/sarashina2.2-3b |
| Model Size | 3b |
| Required VRAM | 6.7 GB |
| Updated | 2025-09-03 |
| Maintainer | sbintuitions |
| Model Type | llama |
| Model Files | |
| Supported Languages | ja en |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives to Sarashina2.2 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 1116 | 4 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1728493 | 1680 |
| Llama 3.2 3B | 128K / 6.5 GB | 576117 | 625 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 1265 | 16 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 8147 | 171 |
| Discord Micae Hermes 3 3B | 128K / 6.5 GB | 2384 | 4 |
| Psychologist 3B | 128K / 6.5 GB | 52 | 5 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 8 | 2 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 2423 | 1 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 29970 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than sbintuitions/sarashina2.2-3b .
Rank the Sarashina2.2 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? 51086 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124