matu79go/Reflex-1-4B
Text Classification • Updated
Reflex-1
Frontier-LLM accuracy at Jev speed with a 4B open model. Skills + base model variants.
Note Skills (LoRA + latent reasoning modules). Start here.
matu79go/Reflex-1-4B-bnb-4bit
Image-Text-to-Text • 8B • Updated • 36Note Base model, pre-quantized 4-bit NF4 (9.3 GB). Recommended.