Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-0.6B
Qwen3 0.6B 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 0.6B Parameters and Internals
| LLM Name | Qwen3 0.6B |
| Repository 🤗 | https://huggingface.co/unsloth/Qwen3-0.6B |
| Base Model(s) | |
| Model Size | 0.6b |
| Required VRAM | 1.2 GB |
| Updated | 2025-07-29 |
| Maintainer | unsloth |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 0.6B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 Reranker 0.6B | 40K / 1.2 GB | 297505 | 175 |
| OuteTTS 1.0 0.6B | 40K / 1.2 GB | 1724 | 88 |
| Qwen3 0.6B FP8 | 40K / 1.1 GB | 4870 | 46 |
| Qwen3 0.6B Medical Expert | 40K / 1.2 GB | 4853 | 3 |
| Qwen3 0.6B Gabliterated | 40K / 1.2 GB | 89 | 7 |
| ...wen3 Zero Coder Reasoning 0.8B | 40K / 1.6 GB | 58 | 0 |
| Qwen3 0.6B Bf16 | 40K / 1.2 GB | 1154 | 5 |
| ...fied Qwen3 0.6B Abliterated V1 | 40K / 1.2 GB | 1118 | 3 |
| Qwen3 0.6B MLX Bf16 | 40K / 1.2 GB | 1250 | 0 |
| Qwen3 0.6B Abliterated | 40K / 1.2 GB | 845 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-0.6B .
Rank the Qwen3 0.6B 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? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124