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

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

Qwen2.5 Coder 32B Instruct is developed by Qwen, 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 Qwen2.5 Coder 32B Instruct perform on standard benchmarks?

Qwen2.5 Coder 32B Instruct has the following published scores: HumanEval (Python) 83.2, LMSYS ELO 1232. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen2.5 Coder 32B Instruct by Qwen — VRAM 65.8GB, 32K context

Name: Qwen2.5 Coder 32B Instruct
Rating: 3 (11 reviews)
Author: Qwen

Qwen2.5 Coder 32B Instruct is an open-source language model by Qwen. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.54, ELO: 1232, HumanEval: 83.2.

Arxiv:2309.00071 Arxiv:2407.10671 Arxiv:2409.12186 Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-... Chat Code Codegen Codeqwen Conversational En Endpoints compatible Instruct Qwen Qwen-coder Qwen2 Region:us Safetensors Sharded Tensorflow

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

Qwen2.5 Coder 32B Instruct Benchmarks

LMSys ELO: 1232 vs 1272 (so35)^-3.1%

IFEval: 72.65 vs 88 (so35)^-17.4%

HumanEvalA: 63.38

Python Eva: 83.2 vs 92 (so35)^-9.6%

Java Eval: 73.69

Javascript: 76.05

CPP Eval: 81.95

PHP Eval: 73.59

Julia Eval: 58.15

D Eval: 26.98

Lua Eval: 46.04

R Eval: 52.73

Racket Eva: 61.54

Rust Eval: 68.53

Swift Eval: 58.12

MATH Lvl 5: 49.55

LLME Score: 0.53969

^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)

Qwen2.5 Coder 32B Instruct (Qwen/Qwen2.5-Coder-32B-Instruct)

🌟 Advertise your project 🚀

Qwen2.5 Coder 32B Instruct Parameters and Internals

Model Type

Causal Language Model

Supported Languages

en (high)

Training Details

Data Sources:

source code, text-code grounding, synthetic data

Data Volume:

5.5 trillion tokens

Context Length:

131072

Model Architecture:

transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

LLM Name	Qwen2.5 Coder 32B Instruct
Repository 🤗	https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct
Base Model(s)	Qwen/Qwen2.5-Coder-32B Qwen/Qwen2.5-Coder-32B
Model Size	32b
Required VRAM	65.8 GB
Updated	2025-09-23
Maintainer	Qwen
Model Type	qwen2
Instruction-Based	Yes
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
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Quantized Models of the Qwen2.5 Coder 32B Instruct

Model	Likes	Downloads	VRAM
....5 Coder 32B Instruct Bnb 4bit	6	5519	19 GB
...wen2.5 Coder 32B Instruct 3bit	4	83	14 GB
SqlCoder Qwen2.5 8bit	3	15	0 GB
Qwen2.5 Coder 32B Instruct AWQ	35	688876	19 GB
...5 Coder 32B Instruct GPTQ Int4	24	13120	19 GB
...wen2.5 Coder 32B Instruct 4bit	12	1635	18 GB
...wen2.5 Coder 32B Instruct 8bit	13	1190	34 GB
...5 Coder 32B Instruct GPTQ Int8	21	1075	35 GB

Best Alternatives to Qwen2.5 Coder 32B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	8	2
Qwen2.5 32B YOYO MIX	128K / 65.7 GB	7	2
Qwen2.5 Coder 32B YOYO	128K / 65.8 GB	8	2
QwQ Qwen2.5 Coder Instruct 32B	128K / 65.8 GB	43	0
QwQenSeek Coder	128K / 65.7 GB	34	5
Rombos Coder V2.5 Qwen 32B	128K / 65.8 GB	24	19
Tessa T1 32B	117K / 65.8 GB	10	22
UIGEN T1.5 32B	117K / 65.8 GB	19	13
Qwen2.5 Coder 32B Instruct	32K / 65.8 GB	1881	7
Qwen2.5 Test 32B It	32K / 65.8 GB	0	10

Rank the Qwen2.5 Coder 32B Instruct 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! 🌟

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

What open-source LLMs or SLMs are you in search of? 53232 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Qwen2.5 Coder 32B Instruct by Qwen

» All LLMs » Qwen » Qwen2.5 Coder 32B Instruct URL Share it on

Qwen2.5 Coder 32B Instruct Benchmarks

Qwen2.5 Coder 32B Instruct Parameters and Internals

Quantized Models of the Qwen2.5 Coder 32B Instruct

Best Alternatives to Qwen2.5 Coder 32B Instruct

Rank the Qwen2.5 Coder 32B Instruct Capabilities

What open-source LLMs or SLMs are you in search of? 53232 in total.