What are the hardware requirements for SWE Dev 7B?

SWE Dev 7B requires approximately 15.2 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 SWE Dev 7B and how large is it?

SWE Dev 7B is developed by zai-org, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate SWE Dev 7B?

SWE Dev 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SWE Dev 7B by zai-org — VRAM 15.2GB, 32K context

Name: SWE Dev 7B
Author: zai-org

SWE Dev 7B is an open-source language model by zai-org. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, License: mit, Instruction-Based, Code Generating, LLM Explorer Score: 0.17.

Arxiv:2506.07636 Codegen Instruct Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/zai-org/SWE-Dev-7B

SWE Dev 7B Parameters and Internals

LLM Name	SWE Dev 7B
Repository 🤗	https://huggingface.co/zai-org/SWE-Dev-7B
Model Size	7b
Required VRAM	15.2 GB
Updated	2026-08-06
Maintainer	zai-org
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 4.3 GB: 3-of-4 1.1 GB: 4-of-4
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.46.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the SWE Dev 7B 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 SWE Dev 7B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 7B Rebase	986K / 15.2 GB	73	2
Qwen2.5 7B Rebase	986K / 15.2 GB	15	2
StockQwen 2.5 7B	128K / 15.2 GB	69	6
DareQwen 2.5 7B	128K / 15.2 GB	11	1
Tessa T1 7B	117K / 15.2 GB	14	10
UIGEN T1.5 7B	117K / 15.2 GB	12	6
Qwen2.5 Coder 7B Instruct	32K / 15.2 GB	2019400	765
...emanticwiki Coder 7B V2 Merged	32K / 15.2 GB	218	0
...Sft Reasoning Official Full Ft	32K / 15.2 GB	464	0
Vibe Coder 7B Max	32K / 15.3 GB	460	1

Note: green Score (e.g. "73.2") means that the model is better than zai-org/SWE-Dev-7B.