GLM-5.3-Flash graftB Q6_K · MTP · ik_llama.cpp 24.2 tok/s GLM-5.3-Flash-graftB.gguf ik_llama.cpp425a2c1dQ6_Krtx-a6000rtx-3090linux1 stream! 2 caveats midagedev 2026-09-18
Qwen3-Coder-Next IQ4_XS · 1 stream · long answer 133 tok/s Qwen3-Coder-Next-IQ4_XS.gguf ik_llama.cppc10fbbccIQ4_XSrtx-3090rtx-a6000linux1 stream! 3 caveats midagedev 2026-09-18
Qwen3.6-35B-A3B UD-Q4_K_XL · 1 stream 140 tok/s Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf ik_llama.cppc10fbbccUD-Q4_K_XLrtx-a6000rtx-3090linux1 stream! 3 caveats midagedev 2026-09-18