ZygAI OSS Flash GGUF

This repository is the GGUF distribution of ZygAI OSS Flash, released as a legacy milestone by ZygAIโ€™s creator at age 23.

The goal is simple: make the model easy to run locally, easy to share, and easy to preserve.

Legacy Note

ZygAI OSS Flash GGUF is part of the same legacy release as ZygAI/ZygAI_OSS_Flash:

  • open-source by intention
  • local-first friendly
  • shared so the work can outlive its original timeline

If this model helps your project, teaching, or experiments, that is exactly what this release was meant for.

Available GGUF files

  • zygai_flash-f16.gguf
  • zygai_flash-q2_k.gguf
  • zygai_flash-q3_k_s.gguf
  • zygai_flash-q3_k_m.gguf
  • zygai_flash-q3_k_l.gguf
  • zygai_flash-q4_0.gguf
  • zygai_flash-q4_k_s.gguf
  • zygai_flash-q4_k_m.gguf
  • zygai_flash-q5_0.gguf
  • zygai_flash-q5_k_s.gguf
  • zygai_flash-q5_k_m.gguf
  • zygai_flash-q6_k.gguf
  • zygai_flash-q8_0.gguf

Recommended quant

Start with:

  • q4_k_m (best default quality/size/speed balance)

Personal Thanks

A huge, heartfelt thank you to Ruby2001, 0daysophie, italian_tech_person, and Julia's Tech Spot.

Your help was not just technical, it was life-changing.
Without you, my life would have been dark.
Thank you for standing with me and helping make ZygAI OSS Flash real.

llama.cpp run example

./llama.cpp/build/bin/llama-cli \
  -m zygai_flash-q4_k_m.gguf \
  -p "Labas! Papasakok trumpฤ… ฤฏkvepianฤiฤ… mintฤฏ." \
  -n 256
Downloads last month
-
GGUF
Model size
2B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ZygAI/ZygAI_OSS_Flash_GGUF

Quantized
(1)
this model