GameScaling 9B S3 needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
GameScaling 9B S3 – a Qwen3.5 vision‑language model trained on gameplay
GameScaling 9B S3 is a Qwen3.5‑based vision‑language model with 8.95 billion parameters. It was continued pre‑trained on 1,600 h of gameplay, including 27 % Minecraft and other games. The model accepts a game frame and a short history of past frames and actions and outputs the next 200 ms of keyboard and mouse actions.
Good at
- Vision‑language gameplay prediction
- Keyboard‑mouse action generation
- Short‑term game state reasoning
Limits
- No text‑only inference without a frame
- Requires a GPU with sufficient VRAM for chosen quant
- License is Apache‑2.0
Best for
- Game AI prototyping
- Real‑time action prediction in virtual environments
- Research on embodied agents
Who it’s for. Developers and researchers building or studying embodied agents in virtual worlds. The model is suitable for those who need vision‑language understanding combined with action generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| F16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.63 GB file, ~7.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (6.47 GB file, ~8.1 GB memory). If more VRAM is available, Q6_K (7.36 GB file, ~9 GB memory) provides higher quality.
What GPU do you need for GameScaling 9B 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_S (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (6.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.5 GB in use).
Which GameScaling 9B S3 quant should you choose?
Q4_K_M is the usual starting point for GameScaling 9B S3: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 GB, about 1.7 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 3.8 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 9B S3
How much VRAM does GameScaling 9B S3 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 9B S3 on an 8 GB GPU?
Yes, with Q5_K_S: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GameScaling 9B S3 GGUF?
It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 more.
What context length does GameScaling 9B 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 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download GameScaling 9B S3 GGUF?
The files are on Hugging Face in the mradermacher/GameScaling-9B-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 9B 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 9B S3 on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 7.2 GB of VRAM at 8k context.
Does the model support text‑only prompts?
No, the model requires a game frame and history of past frames and actions to function.
What license applies to this model?
The model is released under the Apache‑2.0 license.