3 5 minutes ago

NVIDIA Nemotron 3.5 Bolt 74B-A9B Uncensored Hybrid Mamba-2 + MoE (74B total, 9B active, 22.0GB + GGUF <think> patch). 142.1 tok/s Decode, 6932 tok/s Prefill, 78.6% Precision, 0.0% Hallucination (6/6), 100% Zero-Refusal. License: NVIDIA Open / Apache-2.0.

vision tools thinking 74b
9ffc98c19313 ยท 168B
{
"num_ctx": 131072,
"repeat_penalty": 1.1,
"stop": [
"<|im_start|>",
"<|im_end|>",
"<|im_start|>user"
],
"temperature": 0.6,
"top_k": 40,
"top_p": 0.92
}