Who developed GameScaling and how large is it?

GameScaling is developed by THUSI-Lab, a model with 27b 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 GameScaling?

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

GameScaling by THUSI-Lab

Name: GameScaling
Author: THUSI-Lab

GameScaling is an open-source language model by THUSI-Lab. Features: 27b LLM, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b Continued-pretraining Embodied-agent En Endpoints compatible Game-agent Gamescaling Image-text-to-text Keyboard-mouse Qwen3 5 Region:us

Model Card on HF 🤗: https://huggingface.co/THUSI-Lab/GameScaling

GameScaling Parameters and Internals

LLM Name	GameScaling
Repository 🤗	https://huggingface.co/THUSI-Lab/GameScaling
Base Model(s)	Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-2B Qwen/Qwen3.5-9B Qwen/Qwen3.5-27B Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-2B Qwen/Qwen3.5-9B Qwen/Qwen3.5-27B
Model Size	27b
Updated	2026-10-19
Maintainer	THUSI-Lab
Supported Languages	en
Model Architecture	AutoModel
License	apache-2.0

Rank the GameScaling 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 GameScaling

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 27B AmberKite DPO Lora	0K / 0.9 GB	15	1
Longzu DPO Sft Lora	0K / 0 GB	177	1
Marketplace M0 Professional B	0K / 0.3 GB	13	1
...nese Xuanhuan Novel Writer DPO	0K / 0.7 GB	6	1
Medina Qwen3.5 27B OpenClaw	0K / 0.6 GB	2302	14
Gemma4 E2B Qwen3.8 Distilled	0K / 0.1 GB	45	1