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 Aug 5 • 73 • 2 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF Text Generation • 27B • Updated Aug 15 • 58
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 Aug 5 • 73 • 2 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF Text Generation • 27B • Updated Aug 15 • 58
