llama.cpp's Preliminary SM120 Native NVFP4 MMQ Is Merged
·
0 reactions
·
0 comments
·
8 views
And somehow we already got some GGUFs for it! (the below one is from PR author himself)
Original article
LocalLlama
Anonymous · no account needed
Discussion
0 commentsMore from LocalLlama
Blog: AI evals are becoming the new compute bottleneck
LocalLlama·4
Qwen3.6-27B - Closed-loop SVG Images
LocalLlama·2
MiMo-V2.5-Pro - the actual best open-weights model
LocalLlama·4
Update on 2019 Mac Pro
LocalLlama·7
16x Spark Cluster (Build Update)
LocalLlama·7
daily ritual at this point…
LocalLlama·20