What are the hardware requirements for Swe At Scale?

Swe At Scale requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Swe At Scale and how large is it?

Swe At Scale is developed by SWE-at-Scale, a model with 9b 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 At Scale?

Swe At Scale is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Swe At Scale by SWE-at-Scale — VRAM 0.2GB

Name: Swe At Scale
Author: SWE-at-Scale

Swe At Scale is an open-source language model by SWE-at-Scale. Features: 9b LLM, VRAM: 0.2GB.

Adapter Base model:adapter:qwen/qwen3.... Base model:qwen/qwen3.5-9b Bug-injection Finetuned Lora Peft Region:us Safetensors Software-engineering Swe-benchmark

Model Card on HF 🤗: https://huggingface.co/SWE-at-Scale/swe-at-scale

Swe At Scale Parameters and Internals

LLM Name	Swe At Scale
Repository 🤗	https://huggingface.co/SWE-at-Scale/swe-at-scale
Base Model(s)	Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B
Model Size	9b
Required VRAM	0.2 GB
Updated	2026-10-22
Maintainer	SWE-at-Scale
Model Files	0.2 GB
Model Architecture	Adapter
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_proj\|o_proj\|v_proj\|out_proj\|in_proj_a\|q_proj\|up_proj\|down_proj\|in_proj_b\|in_proj_z\|in_proj_qkv\|k_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Swe At Scale 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 At Scale

Best Alternatives	Context / RAM	Downloads	Likes
Kev 9B	0K / 0.2 GB	4206	66
EpiQwen3.5 9B	0K / 0.3 GB	123	1
Nautil SFT	0K / 0.2 GB	49	1
Editppt Vision Validator Lora	0K / 0.2 GB	12	1
Karti Small Support 9B	0K / 0.1 GB	26	1
Imajev 9B	0K / 0.2 GB	35	1
Schierling Qwen3.5 9B LoRA	0K / 0.2 GB	13	0
...kish Lora Continue Pre Trained	0K / 0 GB	3	5
...emma9 On Korean Summary Events	0K / 0.2 GB	6	0
Gemma 2 9B It Lora Yt Titles	0K / 0.1 GB	30	1

Note: green Score (e.g. "73.2") means that the model is better than SWE-at-Scale/swe-at-scale.