Arxiv:2309.00071 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-32b Qwen3 Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-32B
Qwen3 32B 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 32B Parameters and Internals
| LLM Name | Qwen3 32B |
| Repository 🤗 | https://huggingface.co/unsloth/Qwen3-32B |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 65.8 GB |
| Updated | 2025-06-01 |
| Maintainer | unsloth |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 32B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 32B | 40K / 65.6 GB | 883600 | 360 |
| Qwen3 32B FP8 | 40K / 34.5 GB | 40302 | 49 |
| DMind 1 | 40K / 65.8 GB | 175 | 21 |
| Qwen3 32B Abliterated | 40K / 65.8 GB | 1099 | 11 |
| Qwen 3 32B Medical Reasoning | 40K / 65.8 GB | 89 | 1 |
| Qwen3 32B Unsloth Bnb 4bit | 40K / 39.6 GB | 15974 | 7 |
| Qwen3 32B 4bit | 40K / 18.5 GB | 746 | 1 |
| Qwen3 32B 8bit | 40K / 34.9 GB | 406 | 0 |
| Qwen3 32B 128K GGUF | 128K / 7.8 GB | 16397 | 20 |
| Qwen3 32B AWQ | 40K / 19.4 GB | 80024 | 62 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-32B .
Rank the Qwen3 32B 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227