64 Downloads Updated 4 months ago
ollama run uaysk0327/nemotron-3-nano:30b-q4_k_xl
Updated 4 months ago
4 months ago
69fb2351a54f · 23GB ·
Able to use 92160 Context if you enable q8_0 kv cache quantize in 24GB VRAM, ollama’s official model is using q4_k_m and this model is using q4_k_xl so it can be fit in 24GB VRAM