What are the hardware requirements for QwQ Qwen2.5 Coder Instruct 32B?

QwQ Qwen2.5 Coder Instruct 32B requires approximately 65.8 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QwQ Qwen2.5 Coder Instruct 32B and how large is it?

QwQ Qwen2.5 Coder Instruct 32B is developed by sm54, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate QwQ Qwen2.5 Coder Instruct 32B?

QwQ Qwen2.5 Coder Instruct 32B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

QwQ Qwen2.5 Coder Instruct 32B by sm54 — VRAM 65.8GB, 128K context

Name: QwQ Qwen2.5 Coder Instruct 32B
Author: sm54

QwQ Qwen2.5 Coder Instruct 32B is an open-source language model by sm54. Features: 32b LLM, VRAM: 65.8GB, Context: 128K, Instruction-Based, Code Generating, LLM Explorer Score: 0.17.

Autotrain compatible Base model:merge:qwen/qwen2.5-... Base model:merge:qwen/qwen2.5-... Base model:merge:qwen/qwq-32b Base model:qwen/qwen2.5-32b Base model:qwen/qwen2.5-coder-... Base model:qwen/qwq-32b Codegen Conversational Endpoints compatible Instruct Merge Mergekit Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sm54/QwQ-Qwen2.5-Coder-Instruct-32B

QwQ Qwen2.5 Coder Instruct 32B Parameters and Internals

LLM Name	QwQ Qwen2.5 Coder Instruct 32B
Repository 🤗	https://huggingface.co/sm54/QwQ-Qwen2.5-Coder-Instruct-32B
Base Model(s)	Qwen/Qwen2.5-32B Qwen/Qwen2.5-Coder-32B-Instruct QwQ 32B Qwen/Qwen2.5-32B Qwen/Qwen2.5-Coder-32B-Instruct Qwen/QwQ-32B
Model Size	32b
Required VRAM	65.8 GB
Updated	2025-03-16
Maintainer	sm54
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-14 5.0 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 1.9 GB: 14-of-14
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.49.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the QwQ Qwen2.5 Coder Instruct 32B 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 Qwen2.5 Coder Instruct 32B

Best Alternatives	Context / RAM	Downloads	Likes
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
Qwen2.5 32B YOYO MIX	128K / 65.7 GB	8	2
Qwen2.5 Coder 32B YOYO	128K / 65.8 GB	8	2
QwQenSeek Coder	128K / 65.7 GB	20	5
Rombos Coder V2.5 Qwen 32B	128K / 65.8 GB	10	19
Tessa T1 32B	117K / 65.8 GB	12	22
UIGEN T1.5 32B	117K / 65.8 GB	12	13
Qwen2.5 Coder 32B Instruct	32K / 65.8 GB	1265226	2087
Qwen2.5 Coder 32B Instruct	32K / 65.8 GB	2100	7
Qwen2.5 Test 32B It	32K / 65.8 GB	0	10

Note: green Score (e.g. "73.2") means that the model is better than sm54/QwQ-Qwen2.5-Coder-Instruct-32B.