What are the hardware requirements for QwQ 32B Preview?

QwQ 32B Preview requires approximately 65.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QwQ 32B Preview and how large is it?

QwQ 32B Preview is developed by unsloth, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does QwQ 32B Preview perform on standard benchmarks?

QwQ 32B Preview has the following published scores: LMSYS ELO 1154. Compare against reference models on this page or on the LLM Explorer leaderboards.

QwQ 32B Preview by unsloth — VRAM 65.8GB, 32K context

Name: QwQ 32B Preview
Author: unsloth

QwQ 32B Preview is an open-source language model by unsloth. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.27, ELO: 1154.

Arxiv:2407.10671 Autotrain compatible Base model:finetune:qwen/qwq-3... Base model:qwen/qwq-32b-previe... Chat Conversational En Endpoints compatible Qwen Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/unsloth/QwQ-32B-Preview

QwQ 32B Preview Benchmarks

LMSys ELO 1154 vs 1272 (so35) -9.3%

^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 Preview Parameters and Internals

LLM Name	QwQ 32B Preview
Repository 🤗	https://huggingface.co/unsloth/QwQ-32B-Preview
Base Model(s)	QwQ 32B Preview Qwen/QwQ-32B-Preview
Model Size	32b
Required VRAM	65.8 GB
Updated	2025-04-28
Maintainer	unsloth
Model Type	qwen2
Model Files	4.9 GB: 1-of-14 4.9 GB: 2-of-14 4.9 GB: 3-of-14 4.9 GB: 4-of-14 4.9 GB: 5-of-14 4.9 GB: 6-of-14 4.9 GB: 7-of-14 4.9 GB: 8-of-14 4.9 GB: 9-of-14 4.9 GB: 10-of-14 4.9 GB: 11-of-14 4.9 GB: 12-of-14 4.9 GB: 13-of-14 2.1 GB: 14-of-14
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.46.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the QwQ 32B Preview capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to QwQ 32B Preview

Best Alternatives	Context / RAM	Downloads	Likes
Openbuddy Qwq 32B V24.2 200K	195K / 65.8 GB	9	3
Openbuddy Qwq 32B V24.1 200K	195K / 65.8 GB	10	3
Openbuddy Qwq 32B V25.2q 200K	195K / 65.8 GB	1	4
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
DeepSeek R1 Distill Qwen 32B	128K / 65.7 GB	841633	1584
Qwen2.5 32B	128K / 65.5 GB	49206	180
RomboUltima 32B	128K / 20.7 GB	12	6
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	28	17
Ultiima 32B	128K / 65.8 GB	11	7
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	22	4

Note: green Score (e.g. "73.2") means that the model is better than unsloth/QwQ-32B-Preview.