GameScaling 2B S3 needs about 2.5 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.1 GB (Q2_K) to 4.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
GameScaling 2B S3 – Qwen3.5 vision‑language model for game action prediction
GameScaling 2B S3 is a Qwen3.5‑2B model continued pre‑trained on 1,600 h of gameplay. It predicts the next 200 ms of keyboard and mouse actions from a game frame and short history. The model supports reasoning, tools and vision.
Good at
- Game action prediction
- Vision‑language reasoning
- Tool use
Limits
- No vision support beyond game frames
- Large VRAM needed for higher quants
- Apache‑2.0 license limits commercial use
Best for
- Real‑time game AI agents
- Game bot development
- Research on embodied agents
Who it’s for. Developers and researchers building AI agents that interact with games via keyboard and mouse. The model is suitable for those who need vision‑language capabilities and action prediction in virtual environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 2.3 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.7 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.6 GB | 3.5 GB | Fits | Get file → | |
| F16 | 4.8 GB | 5.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.56 GB, memory 2.5 GB). For 12 GB VRAM, Q5_K_M (1.76 GB, 2.7 GB) is a good balance. For 16 GB VRAM, Q6_K (1.97 GB, 2.9 GB) provides higher quality. Estimates are approximate.
What GPU do you need for GameScaling 2B S3?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (2.6 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.8 GB file, about 5.7 GB in use).
Which GameScaling 2B S3 quant should you choose?
Q4_K_M is the usual starting point for GameScaling 2B S3: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.6 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GameScaling 2B S3
How much VRAM does GameScaling 2B S3 need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run GameScaling 2B S3 on an 8 GB GPU?
Yes, with F16: the 4.8 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GameScaling 2B S3 GGUF?
It depends on the quant: Q2_K is 1.1 GB, Q3_K_S is 1.2 GB, Q3_K_M is 1.3 GB, Q3_K_L is 1.4 GB, IQ4_XS is 1.5 GB, Q4_K_S is 1.5 GB and 6 more.
What context length does GameScaling 2B S3 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download GameScaling 2B S3 GGUF?
The files are on Hugging Face in the mradermacher/GameScaling-2B-S3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GameScaling 2B S3 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run GameScaling 2B S3 on 8 GB VRAM?
Yes, use the Q4_K_M quant which requires about 2.5 GB of VRAM at 8 k context.
Does the model support vision tasks?
It processes game frames as visual input, but it is not a general vision model.
What license applies to this model?
The model is released under the Apache‑2.0 license.