oamazonasgabriel/ nemotron-3.5-lightning:q4-24gbGPU

38 5 minutes ago

An open 30B MoE model with ~3B active parameters, packaged by impacte.tech for the execution layer of always-on agents. Uses the official Q4_K_M quant (25 GB). Features native tool calling and thinking modes.

tools thinking
... /
params
1548dfac06fb · 147B
{
"num_ctx": 16384,
"num_gpu": 99,
"repeat_penalty": 1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 1,
"top_k": 20,
"top_p": 0.95
}