What are the hardware requirements for Qwen2.5 Coder 32B Bnb 4bit?

Qwen2.5 Coder 32B Bnb 4bit requires approximately 19.2 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 Bnb 4bit and how large is it?

Qwen2.5 Coder 32B Bnb 4bit 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 Qwen2.5 Coder 32B Bnb 4bit perform on standard benchmarks?

Qwen2.5 Coder 32B Bnb 4bit has the following published scores: HumanEval (Python) 57.1. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen2.5 Coder 32B Bnb 4bit by unsloth — VRAM 19.2GB, 32K context

Name: Qwen2.5 Coder 32B Bnb 4bit
Author: unsloth

Qwen2.5 Coder 32B Bnb 4bit is an open-source language model by unsloth. Features: 32b LLM, VRAM: 19.2GB, Context: 32K, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.18, HumanEval: 57.1.

Arxiv:2407.10671 Arxiv:2409.12186 4-bit 4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Bitsandbytes Code Codegen Codeqwen En Endpoints compatible Quantized Qwen Qwen-coder Qwen2 Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-Coder-32B-bnb-4bit

Qwen2.5 Coder 32B Bnb 4bit Benchmarks

HumanEvalA: 55.07

Python Eva: 57.1 vs 92 (so35)^-37.9%

Java Eval: 65.49

Javascript: 65.07

CPP Eval: 64.35

PHP Eval: 62.7

Julia Eval: 51.28

D Eval: 32.3

Lua Eval: 57.25

R Eval: 31.2

Racket Eva: 47.93

Rust Eval: 65.94

Swift Eval: 60.21

LLME Score: 0.18045

^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 Bnb 4bit (unsloth/Qwen2.5-Coder-32B-bnb-4bit)

🌟 Advertise your project 🚀

Qwen2.5 Coder 32B Bnb 4bit Parameters and Internals

LLM Name	Qwen2.5 Coder 32B Bnb 4bit
Repository 🤗	https://huggingface.co/unsloth/Qwen2.5-Coder-32B-bnb-4bit
Base Model(s)	Qwen/Qwen2.5-Coder-32B Qwen/Qwen2.5-Coder-32B
Model Size	32b
Required VRAM	19.2 GB
Updated	2026-04-28
Maintainer	unsloth
Model Type	qwen2
Model Files	4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 4.3 GB: 4-of-4
Supported Languages	en
Quantization Type	4bit
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.44.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Best Alternatives to Qwen2.5 Coder 32B Bnb 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek R1 Qwen32b Mlx 6bit	128K / 25.5 GB	31	14
....5 Coder 32B Instruct Bnb 4bit	32K / 19.2 GB	5519	6
...wen2.5 Coder 32B Instruct 3bit	32K / 14.3 GB	83	4
...wen2.5 Coder 32B Instruct 4bit	32K / 18.5 GB	2076	12
...wen2.5 Coder 32B Instruct 8bit	32K / 34.9 GB	1110	13
...truct Gptqmodel 4bit Vortex V1	32K / 21.3 GB	69	16
Qwen2.5 Coder 32B 4bit	32K / 18.5 GB	123	3
Qwen2.5 Coder 32B 8bit	32K / 34.9 GB	22	4
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	8	2
...2.5 Godzilla Coder V2 51B 128K	128K / 102.1 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-Coder-32B-bnb-4bit.

Rank the Qwen2.5 Coder 32B Bnb 4bit 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? 53493 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 Bnb 4bit by unsloth

» All LLMs » unsloth » Qwen2.5 Coder 32B Bnb 4bit URL Share it on

Qwen2.5 Coder 32B Bnb 4bit Benchmarks

Qwen2.5 Coder 32B Bnb 4bit Parameters and Internals

Best Alternatives to Qwen2.5 Coder 32B Bnb 4bit

Rank the Qwen2.5 Coder 32B Bnb 4bit Capabilities

What open-source LLMs or SLMs are you in search of? 53493 in total.