LLM EXPLORER 58,178 MODELS INDEXED

Qwen QwQ 32B 425bpw H6 EXL2 by dillonroach

By dillonroach · 5 downloads
HF Repo ↗ Copy URL

Qwen QwQ 32B 425bpw H6 EXL2 is an open-source language model by dillonroach. Features: 32b LLM, VRAM: 18.8GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.17.

  Arxiv:2309.00071   Arxiv:2407.10671 Base model:quantized:qwen/qwq-...   Base model:qwen/qwq-32b   Chat   Conversational   En   Exl2   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dillonroach/Qwen-QwQ-32B-425bpw-h6-exl2 

Qwen QwQ 32B 425bpw H6 EXL2 Parameters and Internals

LLM NameQwen QwQ 32B 425bpw H6 EXL2
Repository 🤗https://huggingface.co/dillonroach/Qwen-QwQ-32B-425bpw-h6-exl2 
Base Model(s)  QwQ 32B   Qwen/QwQ-32B
Model Size32b
Required VRAM18.8 GB
Updated2026-07-28
Maintainerdillonroach
Model Typeqwen2
Model Files  8.5 GB: 1-of-3   8.6 GB: 2-of-3   1.7 GB: 3-of-3
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen QwQ 32B 425bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...Logic Mix 3 32B Mlx OptiQ 5bit128K / 22.3 GB411
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB779551
Hydraulic Deepseek 16bit128K / 65.8 GB520
...k R1 Distill Qwen 32B Bnb 4bit128K / 19.2 GB271729
...till Qwen 32B Abliterated 4bit128K / 18.5 GB8887
QwQ 32B Unsloth Bnb 4bit128K / 22.5 GB17947
...ogito V1 Preview Qwen 32B 4bit128K / 18.5 GB435
...T1 Flash Lightest 32B Mlx 4Bit128K / 18.5 GB2318
QwQ 32B 4bit128K / 18.5 GB13238
QwQ 32B Bnb 4bit128K / 19.2 GB1574
Note: green Score (e.g. "73.2") means that the model is better than dillonroach/Qwen-QwQ-32B-425bpw-h6-exl2.