Back
Ssignal
19
·4 days ago·1 signals
Archived topic · source no longer tracked

I forked Ninfer 3090 and converted it to run on the CMP170HX - doubled my Qwen3.6-35B from llama.cpp

LlamaNVIDIAModel releaseOn-device

Heat trend

Collecting trend data

The percentage is based on available heat signal, not comment count or independent people.

Why it matters

Llama model activity is surfacing — worth tracking for capability changes, ecosystem impact, and availability.