Qwen3.5 2B JP V0.2 is an open-source language model by keitokei1994. Features: 2b LLM, VRAM: 4.4GB, LLM Explorer Score: 0.32.
Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-2b Conversational Dataset:datapilot/zero sft ja ... Ja Japanese Qwen3.5 Qwen3 5 Region:us Safetensors Sft
Model Card on HF 🤗: https://huggingface.co/keitokei1994/Qwen3.5-2B-JP-v0.2
Qwen3.5 2B JP V0.2 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)
Qwen3.5 2B JP V0.2 Parameters and Internals
| LLM Name | Qwen3.5 2B JP V0.2 |
| Repository 🤗 | https://huggingface.co/keitokei1994/Qwen3.5-2B-JP-v0.2 |
| Model Name | unsloth/Qwen3.5-2B |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 4.4 GB |
| Updated | 2026-04-03 |
| Maintainer | keitokei1994 |
| Model Type | qwen3_5 |
| Model Files | |
| Supported Languages | ja |
| Model Architecture | Qwen3_5ForConditionalGeneration |
| Model Max Length | 262144 |
| Transformers Version | 5.3.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|vision_pad|> |
| Errors | replace |
Best Alternatives to Qwen3.5 2B JP V0.2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.5 2B OptiQ 4bit | 0K / 1.4 GB | 5076 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than keitokei1994/Qwen3.5-2B-JP-v0.2 .
Rank the Qwen3.5 2B JP V0.2 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? 52509 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