20 3 days 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
ollama run madkoding/ornith-1.5-9b-iq2m

Details

3 days ago

c7f3ae0cd071 · 4.7GB ·

qwen35
·
8.95B
·
IQ2_M
clip
·
456M
·
F16
{ "num_ctx": 16384, "temperature": 0.5, "top_k": 20, "top_p": 0.95 }
{{- if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{- range .Messages }}{{ if eq

Readme

No readme