Series of various model quants using: https://github.com/turbo-tan/llama.cpp-tq3
mac
maczzzzzz
AI & ML interests
Learning as I go. experimenting with one 16gb AMD card and one 16gb NVIDIA card. seeing what works.
Recent Activity
liked a model 41 minutes ago
jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus updated a model about 7 hours ago
maczzzzzz/Grug-12B-TQ3_4S-GGUF updated a collection about 7 hours ago
TQ3_4S QuantsOrganizations
None yet