Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-1.7B
Qwen3 1.7B 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 1.7B Parameters and Internals
| LLM Name | Qwen3 1.7B |
| Repository 🤗 | https://huggingface.co/unsloth/Qwen3-1.7B |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 3.4 GB |
| Updated | 2025-06-09 |
| 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 1.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 1.7B | 40K / 4 GB | 572930 | 148 |
| ...3 1.7B Instruction Noreasoning | 40K / 3.4 GB | 865 | 12 |
| Qwen3 1.7B FP8 | 40K / 2.6 GB | 5389 | 25 |
| DAN Qwen3 1.7B | 40K / 3.4 GB | 1156 | 8 |
| Qwen3 1.7B Abliterated | 40K / 3.4 GB | 629 | 14 |
| Smoothie Qwen3 1.7B | 40K / 3.4 GB | 478 | 2 |
| Magpie Qwen DiMind 1.7B | 40K / 3.4 GB | 40 | 1 |
| Capricornus MoT 1.7B Supreme1 | 40K / 3.4 GB | 17 | 0 |
| ...fied Qwen3 1.7B Abliterated V1 | 40K / 3.4 GB | 82 | 3 |
| Sculptor Qwen3 Med Reasoning | 40K / 3.4 GB | 27 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-1.7B .
Rank the Qwen3 1.7B 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? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124