SAVRN
Search Contact SAVRN

Open-weight model · Text generation

Qwen2.5-7B

by Qwen Qwen/Qwen2.5-7B

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.

Parameters7.6B
Context131,072
Weights15.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads706.7k

Runs On

What it takes to serve Qwen2.5-7B (7.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 15.2 GB 18.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 7.6 GB 9.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 3.8 GB 4.6 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 Qwen2.5-7B

A 131,072-token context window on a 7.6B-parameter text model is the combination to notice. At 16-bit the weights run 15.2 GB and the working footprint 18.3 GB; the cheapest setup we price is one MI300X with 192 GB at $1.85 per hour on-demand, so most of the card sits empty before the first prompt. At 8-bit the footprint is 9.1 GB, at 4-bit 4.6 GB. The spare memory goes to long inputs and batching.

Apache 2.0 allows commercial use, modification and redistribution with the notices kept, so fine-tuning on your own data and shipping the result stays inside the license. Access is open: 14 files, 15.2 GB, safetensors. Check two things. The name carries no Instruct suffix and the publisher ships both base and instruction-tuned releases, so confirm which one your workload needs. And the paper listed as describing it is the Qwen2 technical report, arXiv:2407.10671.

SAVRN Research, 2026-09-18

Model Card

By Qwen, published under apache-2.0, revision d14972939875.

Introduction

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 condition-setting for chatbots.
  • Long-context Support up to 128K tokens and can generate up to 8K tokens.
  • Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Read the full model card (524 words)

Configuration

Architecture
Qwen2ForCausalLM
Context length (tokens)
131,072
Layers
28
Hidden size
3,584
Feed-forward size
18,944
Attention heads
28
Key/value heads
4
Vocabulary size
152,064
Sliding window (tokens)
131,072
RoPE base
1e+06
Stored precision
bfloat16
Model type
qwen2

Identity and Version

Repository
Qwen/Qwen2.5-7B
Publisher
Qwen
Task
Text generation
Modality
Text
Library
transformers
Parameters
7.6B parameters
Languages
en
Revision
d149729398750b98c0af14eb82c78cfe92750796
First published
2024-09-15
Last updated
2024-09-25

Files and Weights

14 files, 15.2 GB in total. The weights are 4 files totalling 15.2 GB in safetensors.

Weights4 files · 15.2 GB
Configuration3 files · 28.6 KB
Tokenizer4 files · 11.5 MB
Documentation2 files · 15.2 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00004.safetensorsWeights3.9 GB b6d4b6e881d1
model-00002-of-00004.safetensorsWeights3.9 GB 687e8d08dc82
model-00003-of-00004.safetensorsWeights3.9 GB 32652eb23537
model-00004-of-00004.safetensorsWeights3.6 GB b5a2298dddcf
config.jsonConfiguration686 B —
generation_config.jsonConfiguration138 B —
model.safetensors.index.jsonConfiguration27.8 KB —
LICENSEDocumentation11.3 KB —
README.mdDocumentation3.8 KB —
.gitattributesRepository1.5 KB —
merges.txtTokenizer1.7 MB —
tokenizer.jsonTokenizer7.0 MB —
tokenizer_config.jsonTokenizer7.2 KB —
vocab.jsonTokenizer2.8 MB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
15.2 GB
Download from Qwen

Released by Qwen through ModelScope. Read the license.

Built From

Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

BenchmarkConditionsResultReported byRevisionDate
TIGER-Lab/MMLU-Pro Task mmlu_proMetric mmlu_proComparison conditions not established 45 EvalEval
Reported by a third party		 Evaluated revision not stated 2026-06-30

Memory Requirements

PrecisionWeights in memory
As published15.2 GB
16-bit15.2 GB
8-bit7.6 GB
4-bit3.8 GB

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

Built on This Model

Compare Qwen2.5-7B

Questions About Qwen2.5-7B

How much GPU memory does Qwen2.5-7B need?

About 18.3 GB at 16-bit and 4.6 GB at 4-bit: the weights (7.6B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen2.5-7B 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 Qwen2.5-7B commercially?

Yes. Qwen2.5-7B 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 Qwen2.5-7B's context length?

131,072 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

Qwen2.5-7B-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 7.6B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-7B-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 7.6B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-Coder-7B-Instruct

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 7.6B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-Coder-7B-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 7.6B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-Coder-7B

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 7.6B parameters 32,768 tokens transformers
View model

A fast and efficient 7B 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 -7B 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 7.6B parameters 131,072 tokens
View model