TQ3_4S model quants using: https://github.com/turbo-tan/llama.cpp-tq3
mac
maczzzzzz
AI & ML interests
Learning as I go. experimenting with a 16gb AMD 9060xt, 16gb NVIDIA 5060ti and a 32gb Intel B70. seeing what works.
Recent Activity
liked a model about 9 hours ago
badtheorylabs/btl-2-coder liked a model about 9 hours ago
MooreThreads/MusaCoder-27B liked a model about 22 hours ago
sakamakismile/ThinkingCap-Qwen3.6-27B-NVFP4Organizations
None yet
models 8
maczzzzzz/Grug-12B-ROCmFP4_FAST-GGUF
12B • Updated • 705
maczzzzzz/Qwen3.6-27B-MTP-TQ3_4S-GGUF
27B • Updated • 2.7k
maczzzzzz/Qwen3.6-27B-MTP-ROCmFP4_FAST-GGUF
27B • Updated • 420
maczzzzzz/Qwythos-9B-Claude-Mythos-5-1M-MTP-ROCmFP4-COHERENT-GGUF
9B • Updated • 1.71k • 2
maczzzzzz/Ornstein-3.5-9B-V2-ROCmFPX-STRIX_LEAN-GGUF
9B • Updated • 265
maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
23B • Updated • 224 • 1
maczzzzzz/Qwen3.6-14B-A3B-vibetuned-ROCmFPX-STRIX_LEAN-GGUF
14B • Updated • 629 • 1
maczzzzzz/Ornith-1.0-9b-ROCmFPX-STRIX_LEAN-GGUF
9B • Updated • 147
datasets 0
None public yet