Arxiv:2309.00071 Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen3-32b Conversational En Endpoints compatible Gguf Imatrix Q2 Quantized Qwen Qwen3 Region:us Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-32B-128K-GGUF
Qwen3 32B 128K GGUF 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 128K GGUF Parameters and Internals
| LLM Name | Qwen3 32B 128K GGUF |
| Repository 🤗 | https://huggingface.co/unsloth/Qwen3-32B-128K-GGUF |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 7.8 GB |
| Updated | 2025-06-10 |
| Maintainer | unsloth |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q2|q4_k|q5_k |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.0 |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to Qwen3 32B 128K GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 32B GGUF | 40K / 7.8 GB | 46340 | 66 |
| Qwen3 32B Unsloth Bnb 4bit | 40K / 39.6 GB | 15916 | 8 |
| Qwen3 32B 4bit | 40K / 18.5 GB | 968 | 1 |
| Qwen3 32B 8bit | 40K / 34.9 GB | 702 | 0 |
| Qwen3 32B | 40K / 65.6 GB | 926647 | 382 |
| Qwen3 32B AWQ | 40K / 19.4 GB | 103944 | 66 |
| Qwen3 32B FP8 | 40K / 34.5 GB | 41115 | 51 |
| Qwen3 32B | 40K / 65.8 GB | 7293 | 8 |
| DMind 1 | 40K / 65.8 GB | 276 | 21 |
| Qwen3 32B Abliterated | 40K / 65.8 GB | 1099 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-32B-128K-GGUF .
Rank the Qwen3 32B 128K GGUF 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? 48075 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124