QwQ 32B EXL2 8.0bpw is an open-source language model by Dracones. Features: 32b LLM, VRAM: 29.7GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.18.
8-bit Base model:quantized:qwen/qwq-... Base model:qwen/qwq-32b Chat Conversational En Endpoints compatible Exl2 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Dracones/QwQ-32B_exl2_8.0bpw
QwQ 32B EXL2 8.0bpw 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)
QwQ 32B EXL2 8.0bpw Parameters and Internals
| LLM Name | QwQ 32B EXL2 8.0bpw |
| Repository 🤗 | https://huggingface.co/Dracones/QwQ-32B_exl2_8.0bpw |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 29.7 GB |
| Updated | 2026-03-29 |
| Maintainer | Dracones |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | exl2 |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to QwQ 32B EXL2 8.0bpw
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...k R1 Distill Qwen 32B Bnb 4bit | 128K / 19.2 GB | 7398 | 29 |
| ...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 3866 | 46 |
| Hydraulic Deepseek 16bit | 128K / 65.8 GB | 52 | 0 |
| QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 1272 | 47 |
| QwQ 32B 4bit | 128K / 18.5 GB | 242 | 37 |
| ...till Qwen 32B Abliterated 4bit | 128K / 18.5 GB | 549 | 6 |
| ...till Qwen 32B Unsloth Bnb 4bit | 128K / 35.6 GB | 686 | 11 |
| ...ogito V1 Preview Qwen 32B 4bit | 128K / 18.5 GB | 34 | 5 |
| ...T1 Flash Lightest 32B Mlx 4Bit | 128K / 18.5 GB | 151 | 8 |
| QwQ 32B Bnb 4bit | 128K / 19.2 GB | 223 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than Dracones/QwQ-32B_exl2_8.0bpw .
Rank the QwQ 32B EXL2 8.0bpw 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? 53089 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