AI builder. Turning data into intelligence with ML, NLP & LLMs. Prompt engineer by craft, problem solver by nature. Let's build something smart
-
ornith-1.5-9b-q2k
Ornith-1.5-9B quantized to Q2_K (4.06 GB) — a good balance between size and quality. Runs with a 16k context window and leaves 2.1 GB of VRAM free
vision27 Pulls 2 Tags Updated 3 days ago
-
ornith-1.5-9b-iq2m
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
vision20 Pulls 2 Tags Updated 3 days ago
-
ministral-3tools
2 Pulls 1 Tag Updated 3 days ago