uaysk0327/ nemotron-3-nano:30b-q4_k_xl

64 4 months ago

tools
ollama run uaysk0327/nemotron-3-nano:30b-q4_k_xl

Details

4 months ago

69fb2351a54f · 23GB ·

nemotron_h_moe
·
31.6B
·
Q4_K_M
NVIDIA Open Model License Agreement Last Modified: October 24, 2025 This NVIDIA Open Model License A
{ "num_ctx": 92160, "temperature": 0.85, "top_p": 1 }
{{ .Prompt }}

Readme

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