madkoding/ ornith-1.5-9b-iq2m

123 2 months ago

Ornith-1.5-9B quantized to IQ2_M (3.77 GB) — the most aggressive compression available for this model. Ideal for low-VRAM GPUs. Runs with a 16k context window while leaving 2.5 GB of VRAM free. Slightly faster at the cost of some precision

vision

2 models

ornith-1.5-9b-iq2m:latest
c7f3ae0cd071 • 4.7GB • 256K context window •
Text, Image input • 2 months ago
ornith-1.5-9b-iq2m:1.5-9b
c7f3ae0cd071 • 4.7GB • 256K context window •
Text, Image input • 2 months ago