GA

GameScaling 27B S1

GamescalingGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters26.9B
Context256K
Layers65
Architectureqwen35
Smallest quant10.7 GB
Quick answer

GameScaling 27B S1 needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

GameScaling 27B S1 – Qwen3.5 vision‑language model trained on Minecraft gameplay

GameScaling 27B S1 is a Qwen3.5‑27B model continued pre‑trained on 1,600 h of Minecraft gameplay. It receives a game frame and a short history of past frames and actions, and outputs the next 200 ms of keyboard and mouse actions. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑language reasoning
  • Game action prediction
  • Tool usage

Limits

  • No vision support outside game frames
  • Large VRAM requirement for full precision
  • Apache‑2.0 license

Best for

  • Game AI prototyping
  • Real‑time action generation
  • Research on embodied agents

Who it’s for. Developers and researchers building AI agents for video games. The model is suited for those who need a vision‑language model that can predict short‑term game actions based on recent frames and actions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.7 GB 13.4 GB
Too big Get file →
Q3_K_S12.1 GB 14.8 GB
Too big Get file →
Q3_K_M13.3 GB 16.0 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.2 GB 17.9 GB
Too big Get file →
Q4_K_S15.6 GB 18.3 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_S18.7 GB 21.4 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.8 GB
Too big Get file →
Q8_028.6 GB 31.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 15.59 GB, estimated 18.3 GB memory). For 12 GB VRAM, Q5_K_S (file size 18.68 GB, estimated 21.4 GB memory) is a good balance. For 16 GB VRAM, Q6_K (file size 22.08 GB, estimated 24.8 GB memory) provides higher quality.

What GPU do you need for GameScaling 27B S1?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.3 GB in use).

Which GameScaling 27B S1 quant should you choose?

Q4_K_M is the usual starting point for GameScaling 27B S1: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 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 10.7 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

Architectureqwen35
Parameters26.9B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)870
Last updated2026-10-15

Frequently asked questions about GameScaling 27B S1

How much VRAM does GameScaling 27B S1 need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 27B S1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GameScaling 27B S1 GGUF?

It depends on the quant: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.

What context length does GameScaling 27B S1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download GameScaling 27B S1 GGUF?

The files are on Hugging Face in the mradermacher/GameScaling-27B-S1-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 27B S1 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 27B S1 on 8 GB VRAM?

Use the Q4_K_S quant, which requires about 18.3 GB of VRAM at 8 k context. 8 GB is insufficient.

Does the model support vision outside of game frames?

No, the model is designed to process game frames only.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gamescaling models

All Gamescaling →

Other medium models

All medium models →