GA

GameScaling 2B S1

GamescalingGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters2.39B
Context256K
Layers25
Architectureqwen35
Smallest quant1.1 GB
Quick answer

GameScaling 2B S1 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 S1 – Qwen3.5 vision‑language model trained on Minecraft gameplay

GameScaling 2B S1 is a Qwen3.5‑2B model fine‑tuned on 1,600 h of Minecraft gameplay. It predicts the next 200 ms of keyboard and mouse actions from the current game frame and a short history. The model is available in multiple GGUF quantizations.

Good at

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

Limits

  • No vision support beyond game frames
  • Limited to 262,144 context tokens
  • Apache‑2.0 license

Best for

  • Game AI prototyping
  • Real‑time action prediction
  • Embedded game agents

Who it’s for. Developers building AI agents for virtual worlds. Researchers needing a vision‑language model trained on gameplay data. Engineers deploying lightweight inference on limited hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 2.1 GB
Fits Get file →
Q3_K_S1.2 GB 2.2 GB
Fits Get file →
Q3_K_M1.3 GB 2.2 GB
Fits Get file →
Q3_K_L1.4 GB 2.3 GB
Fits Get file →
IQ4_XS1.5 GB 2.4 GB
Fits Get file →
Q4_K_S1.5 GB 2.4 GB
Fits Get file →
Q4_K_M1.6 GB 2.5 GB
Fits Get file →
Q5_K_S1.7 GB 2.6 GB
Fits Get file →
Q5_K_M1.8 GB 2.7 GB
Fits Get file →
Q6_K2.0 GB 2.9 GB
Fits Get file →
Q8_02.6 GB 3.5 GB
Fits Get file →
F164.8 GB 5.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.56 GB, ~2.5 GB memory). For 4 GB VRAM, Q3_K_S (1.24 GB, ~2.2 GB memory). For 2 GB VRAM, Q2_K (1.14 GB, ~2.1 GB memory). Estimates are approximate.

What GPU do you need for GameScaling 2B 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: 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 S1 quant should you choose?

Q4_K_M is the usual starting point for GameScaling 2B S1: 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

Architectureqwen35
Parameters2.39B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,699
Last updated2026-10-15

Frequently asked questions about GameScaling 2B S1

How much VRAM does GameScaling 2B S1 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 S1 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 S1 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 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 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download GameScaling 2B S1 GGUF?

The files are on Hugging Face in the mradermacher/GameScaling-2B-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 2B 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 2B S1 on 8 GB VRAM?

Yes, use the Q4_K_M quantization; it requires about 2.5 GB VRAM at 8 k context.

Does the model support vision?

It processes game frames as input but is not a general vision model; it is designed for game frames only.

What license does it use?

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 tiny models

All tiny models →