Qwen2.5-Coder-32B-Instruct by Qwen: Open-Weight Model

Runs On

What it takes to serve Qwen2.5-Coder-32B-Instruct (32.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Weights	Memory needed	Cheapest setup	Per hour	Also fits
16-bit	65.5 GB	78.6 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	32.8 GB	39.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	16.4 GB	19.7 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on Qwen2.5-Coder-32B-Instruct

78.6 GB is the number to plan around. At 16-bit the weights are 65.5 GB and need 78.6 GB once loaded, which fits one 192 GB MI300X at the cheapest rate we track, $1.85 an hour on-demand. At 8-bit the footprint drops to 39.3 GB and at 4-bit to 19.7 GB, so a single card carries any precision you choose. It is the largest of six Qwen2.5-Coder sizes, which run from 0.5 to 32 billion parameters, and this is the instruct version built on the Qwen2.5-Coder-32B base, meant for code generation, code reasoning and code fixing in conversation rather than raw completion.

Apache 2.0 allows commercial use, modification and redistribution as long as you keep the license and copyright notices and state significant changes. Check the 32,768-token context against your longest files, and weigh the $1.85 card against the one host on the SAVRN Index, Nscale, at $0.06 in and $0.20 out per million tokens; that comparison shows where your own volume starts paying for the hardware.

SAVRN Research, 2026-09-18

Model Card

By Qwen, published under apache-2.0, revision 381fc969f78e.

Introduction

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.
Long-context Support up to 128K tokens.

Read the full model card (760 words)

Configuration

Architecture: Qwen2ForCausalLM
Context length (tokens): 32,768
Layers: 64
Hidden size: 5,120
Feed-forward size: 27,648
Attention heads: 40
Key/value heads: 8
Vocabulary size: 152,064
Sliding window (tokens): 131,072
RoPE base: 1e+06
Stored precision: bfloat16
Model type: qwen2

Identity and Version

Repository: Qwen/Qwen2.5-Coder-32B-Instruct
Publisher: Qwen
Task: Text generation
Modality: Text
Library: transformers
Parameters: 32.8B parameters
Languages: en
Revision: 381fc969f78efac66bc87ff7ddeadb7e73c218a7
First published: 2024-11-06
Last updated: 2025-01-12

Files and Weights

24 files, 65.5 GB in total. The weights are 14 files totalling 65.5 GB in safetensors.

Weights14 files · 65.5 GB

Configuration3 files · 64.2 KB

Tokenizer4 files · 11.5 MB

Documentation2 files · 17.7 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model-00001-of-00014.safetensors	Weights	4.9 GB	5746929d771e
model-00002-of-00014.safetensors	Weights	4.9 GB	12aaad653a85
model-00003-of-00014.safetensors	Weights	4.9 GB	9bac433064b2
model-00004-of-00014.safetensors	Weights	4.9 GB	4e859e864a61
model-00005-of-00014.safetensors	Weights	4.9 GB	57000579cf2e
model-00006-of-00014.safetensors	Weights	4.9 GB	72dd80465092
model-00007-of-00014.safetensors	Weights	4.9 GB	b91130f8049d
model-00008-of-00014.safetensors	Weights	4.9 GB	522db6c67390
model-00009-of-00014.safetensors	Weights	4.9 GB	7c03b072b4aa
model-00010-of-00014.safetensors	Weights	4.9 GB	c5ee9a4665ae
model-00011-of-00014.safetensors	Weights	4.9 GB	49f60205e190
model-00012-of-00014.safetensors	Weights	4.9 GB	9a53a0d4a02d
model-00013-of-00014.safetensors	Weights	4.9 GB	8b26127defc6
model-00014-of-00014.safetensors	Weights	2.1 GB	983ebbded19c
config.json	Configuration	663 B	—
generation_config.json	Configuration	243 B	—
model.safetensors.index.json	Configuration	63.2 KB	—
LICENSE	Documentation	11.3 KB	—
README.md	Documentation	6.4 KB	—
.gitattributes	Repository	1.5 KB	—
merges.txt	Tokenizer	1.7 MB	—
tokenizer.json	Tokenizer	7.0 MB	—
tokenizer_config.json	Tokenizer	7.3 KB	—
vocab.json	Tokenizer	2.8 MB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 65.5 GB

Download from Qwen

Released by Qwen through ModelScope. Read the license.

Built From

Derived from Qwen/Qwen2.5-Coder-32B
Described by arXiv:2309.00071
Described by arXiv:2407.10671
Described by arXiv:2409.12186

Memory Requirements

Precision	Weights in memory
As published	65.5 GB
16-bit	65.5 GB
8-bit	32.8 GB
4-bit	16.4 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Hosted Prices

Host	Input / output	Unit	Observed
Nscale	$0.06 / $0.20	input / output, per million tokens	Sep 18, 2026

From the SAVRN Index.

Built on This Model

Quantized fromQwen2.5-Coder-32B-Instruct-AWQ
Derived fromQwen2.5-Coder-32B-Instruct-AWQ

Compare Qwen2.5-Coder-32B-Instruct

Questions About Qwen2.5-Coder-32B-Instruct

How much GPU memory does Qwen2.5-Coder-32B-Instruct need?

About 78.6 GB at 16-bit and 19.7 GB at 4-bit: the weights (32.8B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen2.5-Coder-32B-Instruct on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen2.5-Coder-32B-Instruct commercially?

Yes. Qwen2.5-Coder-32B-Instruct is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is Qwen2.5-Coder-32B-Instruct's context length?

32,768 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

Qwen2.5-32B-Instruct

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 32.8B parameters 32,768 tokens transformers

View model

Model · Text generation

Qwen2.5-Coder-32B-Instruct-AWQ

Qwen

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. - A more…

Open weights apache-2.0 32.8B parameters 32,768 tokens transformers

View model

Model · Text generation

Qwen2.5-32B-Instruct-AWQ

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 32.8B parameters 32,768 tokens transformers

View model

Model · Text generation

JiRackUltra_32b

Center Business Solutions inc

A fast and efficient 32B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Media, Vision, Sound, Tool call, and Robotics tags. Built on a DeepSeek R1-32B architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer…

Open weights mit 32.8B parameters 131,072 tokens

View model

Model · Text generation

Qwen3-32B

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

View model

Model · Text generation

Qwen3-32B-AWQ

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

View model