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

Qwen2.5 Coder 32B Instruct 4bit requires approximately 18.5 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 4bit and how large is it?

Qwen2.5 Coder 32B Instruct 4bit is developed by mlx-community, 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 4bit perform on standard benchmarks?

Qwen2.5 Coder 32B Instruct 4bit has the following published scores: HumanEval (Python) 83.2. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen2.5 Coder 32B Instruct 4bit by mlx-community — VRAM 18.5GB, 32K context

Name: Qwen2.5 Coder 32B Instruct 4bit
Author: mlx-community

Qwen2.5 Coder 32B Instruct 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 18.5GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.17, HumanEval: 83.2.

4-bit 4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Chat Code Codegen Codeqwen Conversational Deploy:azure En Endpoints compatible Instruct Mlx Quantized Qwen Qwen-coder Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-4bit

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

LLM Name	Qwen2.5 Coder 32B Instruct 4bit
Repository 🤗	https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-4bit
Base Model(s)	Qwen/Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct
Model Size	32b
Required VRAM	18.5 GB
Updated	2026-07-27
Maintainer	mlx-community
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.4 GB: 1-of-4 5.3 GB: 2-of-4 5.4 GB: 3-of-4 2.4 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	4.43.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen2.5 Coder 32B Instruct 4bit 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 Qwen2.5 Coder 32B Instruct 4bit

Best Alternatives	Context / RAM	Downloads	Likes
....5 Coder 32B Instruct Bnb 4bit	32K / 19.2 GB	5519	6
...wen2.5 Coder 32B Instruct 3bit	32K / 14.3 GB	144	4
...wen2.5 Coder 32B Instruct 8bit	32K / 34.9 GB	934	14
...truct Gptqmodel 4bit Vortex V1	32K / 21.3 GB	83	16
...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
QwQ Qwen2.5 Coder Instruct 32B	128K / 65.8 GB	43	0
QwQenSeek Coder	128K / 65.7 GB	20	5
Rombos Coder V2.5 Qwen 32B	128K / 65.8 GB	10	19

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