Pym Aggressive mixed-precision GGUF quants — shrink models to a fraction of their size, keep their edge and speed. Runs on llama.cpp (AMD/Apple too). SGLabs/Qwen3.6-35B-A3B-Pym-Q2-MTP Text Generation • 36B • Updated 7 days ago • 873 • 1
Pym Aggressive mixed-precision GGUF quants — shrink models to a fraction of their size, keep their edge and speed. Runs on llama.cpp (AMD/Apple too). SGLabs/Qwen3.6-35B-A3B-Pym-Q2-MTP Text Generation • 36B • Updated 7 days ago • 873 • 1
