# Qwen2.5-7B-Instruct by Qwen: Open-Weight Model
Source: https://savrn.com/models/qwen2-5-7b-instruct
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve Qwen2.5-7B-Instruct (7.6B 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 | 15.2 GB | 18.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 8-bit | 7.6 GB | 9.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 4-bit | 3.8 GB | 4.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026.

[Qwen2.5-7B-Instruct on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen2-5-7b-instruct/gpus)

## SAVRN's Notes on Qwen2.5-7B-Instruct

7.6B parameters, 18.3 GB at 16-bit, 4.6 GB at 4-bit, on one 192 GB MI300X at $1.85 an hour — a single card serves this at any precision, which is why it stays the default self-hosted mid-size workhorse at 9.7M downloads a month. Qwen built the 2.5 instruct line for structured work: reading tables, writing JSON, generating past 8K tokens.

Apache 2.0 lets you ship it in a product, fine-tuned or not. The official quantized build Qwen2.5-7B-Instruct-AWQ is listed on the page and is the sane 4-bit pick over community conversions. The page states 32,768 tokens of context and cites the YaRN context-extension paper (arXiv:2309.00071), so confirm which window your serving stack actually honors. No host quotes it by the token on our Index — the card hour is your cost basis.

SAVRN Research

## Model Card

By Qwen, published under apache-2.0, revision a09a35458c70.

### 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 (753 words)](https://savrn.com/models/qwen2-5-7b-instruct/card)

## Configuration

Architecture

Qwen2ForCausalLM

Context length (tokens)

32,768

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-Instruct

Publisher

Qwen

Task

Text generation

Modality

Text

Library

transformers

Parameters

7.6B parameters

Languages

en

Revision

a09a35458c702b33eeacc393d103063234e8bc28

First published

2024-09-16

Last updated

2025-01-12

## 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 · 28.7 KB

Tokenizer4 files · 11.5 MB

Documentation2 files · 17.6 KB

Repository1 file · 1.5 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model-00001-of-00004.safetensors | Weights | 3.9 GB | a1333e629385 |
| model-00002-of-00004.safetensors | Weights | 3.9 GB | f5d25a2772cb |
| model-00003-of-00004.safetensors | Weights | 3.9 GB | 8efdec4c1bc1 |
| model-00004-of-00004.safetensors | Weights | 3.6 GB | 1a72d403cdf0 |
| config.json | Configuration | 663 B | — |
| generation_config.json | Configuration | 243 B | — |
| model.safetensors.index.json | Configuration | 27.8 KB | — |
| LICENSE | Documentation | 11.3 KB | — |
| README.md | Documentation | 6.2 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

15.2 GB

[Download from Qwen](https://modelscope.cn/models/Qwen/Qwen2.5-7B-Instruct)

Released by Qwen through ModelScope. [Read the license](https://www.apache.org/licenses/LICENSE-2.0).

## Built From

- Derived from [Qwen/Qwen2.5-7B](https://savrn.com/models/qwen2-5-7b)
- Described by [arXiv:2309.00071](https://savrn.com/papers/yarn-efficient-context-window-extension-of-large-language-models)
- Described by [arXiv:2407.10671](https://savrn.com/papers/qwen2-technical-report)

## 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.

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| LEXam-Benchmark/LEXam | Task mcq_4_choicesMetric mcq_4_choicesComparison conditions not established | 29.28 | LEXam Leaderboard Reported by a third party | Evaluated revision not stated | 2026-06-02 |
| LEXam-Benchmark/LEXam | Task open_questionMetric open_questionComparison conditions not established | 16.67 | LEXam Leaderboard Reported by a third party | Evaluated revision not stated | 2026-06-02 |
| thamilvendhan/signalbench | Task access_denyMetric access_denySetup family=access_deny; n=12Comparison conditions not established | 0.1667 | [thamilvendhan](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |
| thamilvendhan/signalbench | Task bot_policyMetric bot_policySetup family=bot_policy; n=12Comparison conditions not established | 0.3333 | [thamilvendhan](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |
| thamilvendhan/signalbench | Task injectionMetric injectionSetup family=injection; n=12Comparison conditions not established | 0.5 | [thamilvendhan](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |
| thamilvendhan/signalbench | Task memory_labelMetric memory_labelSetup family=memory_label; n=12Comparison conditions not established | 0.5 | [thamilvendhan](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |
| thamilvendhan/signalbench | Task srcMetric srcSetup SRC overall; deterministic action-based grader, no LLM judge; seed 0, n=75Comparison conditions not established | 0.3833 | [signalbench raw per-item responses](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |
| thamilvendhan/signalbench | Task timeMetric timeSetup family=time; n=12Comparison conditions not established | 0.4167 | [thamilvendhan](https://huggingface.co/datasets/thamilvendhan/signalbench) Reported by a third party | Evaluated revision not stated | 2026-07-08 |

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 15.2 GB |
| 16-bit | 15.2 GB |
| 8-bit | 7.6 GB |
| 4-bit | 3.8 GB |

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

## Built on This Model

- Quantized from[Qwen2.5-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-7b-instruct-awq)
- Derived from[Qwen2.5-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-7b-instruct-awq)
- Derived from[Vidhi-AI-Instruct](https://savrn.com/models/vidhi-ai-instruct)
- Adapter of[SajiloFit-FitnessAndNutrition-Qwen2.5-Finetuned](https://savrn.com/models/sajilofit-fitnessandnutrition-qwen2-5-finetuned)
- Derived from[SajiloFit-FitnessAndNutrition-Qwen2.5-Finetuned](https://savrn.com/models/sajilofit-fitnessandnutrition-qwen2-5-finetuned)
- Derived from[Emomni-v1](https://savrn.com/models/emomni-v1)
- Derived from[dolphin-cyber-arabic](https://savrn.com/models/dolphin-cyber-arabic)
- Derived from[Qwen-2.5](https://savrn.com/models/qwen-2-5)
- Adapter of[PG-Personalization-ckpt](https://savrn.com/models/pg-personalization-ckpt)
- Derived from[PG-Personalization-ckpt](https://savrn.com/models/pg-personalization-ckpt)
- Derived from[qwen2.5-7b-fve-workanchor-s0](https://savrn.com/models/qwen2-5-7b-fve-workanchor-s0)
- Derived from[qwen2.5-7b-fve-flouranchor-s0](https://savrn.com/models/qwen2-5-7b-fve-flouranchor-s0)
- Derived from[qwen2.5-7b-fve-advanchor-s0](https://savrn.com/models/qwen2-5-7b-fve-advanchor-s0)
- Adapter of[sn56-i66-s20k](https://savrn.com/models/sn56-i66-s20k)
- Derived from[sn56-i66-s20k](https://savrn.com/models/sn56-i66-s20k)
- Adapter of[dsa-research-lora](https://savrn.com/models/dsa-research-lora)
- Derived from[dsa-research-lora](https://savrn.com/models/dsa-research-lora)
- Adapter of[abc](https://savrn.com/models/abc)
- Derived from[abc](https://savrn.com/models/abc)
- Adapter of[NyayMitra](https://savrn.com/models/nyaymitra)
- Derived from[NyayMitra](https://savrn.com/models/nyaymitra)
- Adapter of[distilling-safety-adapters](https://savrn.com/models/distilling-safety-adapters)
- Derived from[distilling-safety-adapters](https://savrn.com/models/distilling-safety-adapters)
- Adapter of[theo_qwen2.5-7b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-7b-it-loyalty-dpo-lora)
- Derived from[theo_qwen2.5-7b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-7b-it-loyalty-dpo-lora)
- Derived from[SkillForge_Search_7B](https://savrn.com/models/skillforge-search-7b)
- Derived from[SkillForge_Webshop_7B](https://savrn.com/models/skillforge-webshop-7b)
- Derived from[SkillForge_Alfworld_7B](https://savrn.com/models/skillforge-alfworld-7b)
- Adapter of[keural-mid-vlm-bilingual](https://savrn.com/models/keural-mid-vlm-bilingual)
- Derived from[keural-mid-vlm-bilingual](https://savrn.com/models/keural-mid-vlm-bilingual)
- Adapter of[OPSD-SDPO-v22-Qwen2.5-7B-checkpoints](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-7b-checkpoints)
- Derived from[OPSD-SDPO-v22-Qwen2.5-7B-checkpoints](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-7b-checkpoints)
- Adapter of[LLM_Crystal_CIF](https://savrn.com/models/llm-crystal-cif)
- Derived from[LLM_Crystal_CIF](https://savrn.com/models/llm-crystal-cif)
- Adapter of[Qwen2.5-7B-Instruct-Conceptizer](https://savrn.com/models/qwen2-5-7b-instruct-conceptizer)
- Derived from[Qwen2.5-7B-Instruct-Conceptizer](https://savrn.com/models/qwen2-5-7b-instruct-conceptizer)
- Derived from[MemDuet-S2-7B](https://savrn.com/models/memduet-s2-7b)
- Adapter of[OPSD-SDPO-v22-Qwen2.5-7B-LoRA](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-7b-lora)
- Derived from[OPSD-SDPO-v22-Qwen2.5-7B-LoRA](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-7b-lora)

## Compare Qwen2.5-7B-Instruct

- [Qwen2.5-7B-Instruct vs Qwen2.5-Coder-7B](https://savrn.com/models/compare/qwen2-5-7b-instruct-vs-qwen2-5-coder-7b)
- [Qwen2.5-7B-Instruct vs Qwen2.5-Coder-7B-Instruct](https://savrn.com/models/compare/qwen2-5-7b-instruct-vs-qwen2-5-coder-7b-instruct)
- [Mistral-7B-Instruct-v0.2 vs Qwen2.5-7B-Instruct](https://savrn.com/models/compare/mistral-7b-instruct-v0-2-vs-qwen2-5-7b-instruct)

## Questions About Qwen2.5-7B-Instruct

### How much GPU memory does Qwen2.5-7B-Instruct 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-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 Qwen2.5-7B-Instruct commercially?

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

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

## Similar Models

Model · Text generation

### [Qwen2.5-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-7b-instruct-awq)

[Qwen](https://savrn.com/model-publishers/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](https://savrn.com/models/qwen2-5-7b-instruct-awq)

Model · Text generation

### [Qwen2.5-Coder-7B-Instruct](https://savrn.com/models/qwen2-5-coder-7b-instruct)

[Qwen](https://savrn.com/model-publishers/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](https://savrn.com/models/qwen2-5-coder-7b-instruct)

Model · Text generation

### [Qwen2.5-Coder-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-coder-7b-instruct-awq)

[Qwen](https://savrn.com/model-publishers/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](https://savrn.com/models/qwen2-5-coder-7b-instruct-awq)

Model · Text generation

### [Qwen2.5-Coder-7B](https://savrn.com/models/qwen2-5-coder-7b)

[Qwen](https://savrn.com/model-publishers/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](https://savrn.com/models/qwen2-5-coder-7b)

Model · Text generation

### [Qwen2.5-7B](https://savrn.com/models/qwen2-5-7b)

[Qwen](https://savrn.com/model-publishers/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 131,072 tokens transformers

[View model](https://savrn.com/models/qwen2-5-7b)

Model · Text generation

### [JiRackUltra_7b](https://savrn.com/models/jirackultra-7b)

[Center Business Solutions inc](https://savrn.com/model-publishers/cmsmanhattan)

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](https://savrn.com/models/jirackultra-7b)

## Qwen

[All models and datasets](https://savrn.com/model-publishers/qwen)

## Versions

- [a09a35458c70](https://savrn.com/models/qwen2-5-7b-instruct/versions/a09a35458c70) · current 2026-10-25

## In Collections

- [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-on-one-accelerator)
- [Open-weight text models worth knowing](https://savrn.com/collections/open-weight-text-models-worth-knowing)

## Explore More

- [All text generation models](https://savrn.com/models/tasks/text-generation)
- [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0)
- [Model comparisons](https://savrn.com/models/comparisons)
- [The model directory](https://savrn.com/models)
- [Open model prices by host](https://savrn.com/ai-index/pricing/open-models)

## Source

- Repository metadata, read 2026-10-19.
- [Qwen website](https://qwen.ai/)
- [Hugging Face record](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
- [How the hub is built](https://savrn.com/model-hub/methodology)