BY

ByteCraft

BytecraftGGUF by bartowskiUpdated 2025-03-20
Download on Hugging Face
Parameters8.39B
Context32K
Layers28
Architectureqwen2
Smallest quant3.2 GB
Quick answer

ByteCraft needs about 6.2 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 3.2 GB (IQ2_M) to 16.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ByteCraft – a generative model for SWF video games and animations

ByteCraft is a generative model that creates SWF video games and animations from text prompts. It is based on the qwen2 architecture and contains 8.39 billion parameters. The model supports tool usage and is released under the MIT license.

Good at

  • Generating SWF video game content
  • Creating animations from prompts
  • Tool‑based interactions

Limits

  • No vision support
  • Requires 32 k context for training
  • License is MIT

Best for

  • Game developers prototyping SWF assets
  • Animation designers experimenting with text‑to‑animation
  • Researchers exploring generative game content

Who it’s for. Developers and researchers who need a lightweight model for generating SWF video games and animations. The model is suitable for those who can run it with llama.cpp or LM Studio and who are comfortable with a text‑only interface.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M3.2 GB 4.2 GB
Fits Get file →
Q2_K3.5 GB 4.4 GB
Fits Get file →
IQ3_XXS3.5 GB 4.5 GB
Fits Get file →
IQ3_XS3.8 GB 4.8 GB
Fits Get file →
Q3_K_S4.0 GB 4.9 GB
Fits Get file →
IQ3_M4.1 GB 5.0 GB
Fits Get file →
Q3_K_M4.3 GB 5.3 GB
Fits Get file →
Q2_K_L4.4 GB 5.3 GB
Fits Get file →
Q3_K_L4.6 GB 5.5 GB
Fits Get file →
IQ4_XS4.7 GB 5.7 GB
Fits Get file →
IQ4_NL5.0 GB 5.9 GB
Fits Get file →
Q4_05.0 GB 6.0 GB
Fits Get file →
Q4_K_S5.0 GB 6.0 GB
Fits Get file →
Q4_K_M5.2 GB 6.2 GB
Fits Get file →
Q3_K_XL5.4 GB 6.4 GB
Fits Get file →
Q4_15.4 GB 6.4 GB
Fits Get file →
Q5_K_S5.9 GB 6.9 GB
Fits Get file →
Q4_K_L5.9 GB 6.9 GB
Fits Get file →
Q5_K_M6.0 GB 7.0 GB
Fits Get file →
Q5_K_L6.6 GB 7.6 GB
Tight Get file →
Q6_K6.9 GB 7.9 GB
Tight Get file →
Q6_K_L7.3 GB 8.3 GB
Too big Get file →
Q8_08.9 GB 9.9 GB
Too big Get file →
BF1616.8 GB 17.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (file size 3.22 GB, estimated 4.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (5.22 GB, 6.2 GB memory) is a good balance. If more memory is available, Q5_K_M (6.03 GB, 7 GB memory) offers higher precision.

What GPU do you need for ByteCraft?

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 Q4_K_S (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.9 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.8 GB file, about 17.8 GB in use).

Which ByteCraft quant should you choose?

Q4_K_M is the usual starting point for ByteCraft: it balances file size and quality well. Here it is a 5.2 GB file.

The Q8_0 file is 8.9 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 IQ2_M at 3.2 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

Architectureqwen2
Parameters8.39B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized bybartowski
FamilyBytecraft
Licensemit
Downloads (HF)733
Last updated2025-03-20

Frequently asked questions about ByteCraft

How much VRAM does ByteCraft need?

About 6.2 GB at Q4_K_M with an 8K context window. That is the 5.2 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 ByteCraft on an 8 GB GPU?

Yes, with Q6_K: the 6.9 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 ByteCraft GGUF?

It depends on the quant: IQ2_M is 3.2 GB, Q2_K is 3.5 GB, IQ3_XXS is 3.5 GB, IQ3_XS is 3.8 GB, Q3_K_S is 4.0 GB, IQ3_M is 4.1 GB and 18 more.

What context length does ByteCraft support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download ByteCraft GGUF?

The files are on Hugging Face in the bartowski/SamsungSAILMontreal_ByteCraft-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 ByteCraft use?

Hugging Face lists the license as mit. 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 ByteCraft on 8 GB VRAM?

Yes, the IQ2_M quantization requires about 4.2 GB memory at 8 k context, which fits within 8 GB VRAM.

Does ByteCraft support image or video input?

No, ByteCraft is a text‑only model and does not support vision or video input.

Other GGUFs of ByteCraft

Similar models

Browse all →

More from bartowski

All by bartowski →

More Bytecraft models

All Bytecraft →

Other small models

All small models →