This is just my test with imatrix, quality unknown. I don't even know if I did it correctly...


JoyAI-LLM-Flash-GGUF

Weighted/imatrix quants of jdopensource/JoyAI-LLM-Flash using tomngdev/imatrix-calibration-data for calibration.

Downloads last month
1,681
GGUF
Model size
49B params
Architecture
deepseek2
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tomngdev/JoyAI-LLM-Flash-imatrix-GGUF

Quantized
(18)
this model

Dataset used to train tomngdev/JoyAI-LLM-Flash-imatrix-GGUF