5.01 BPW iMatrix/NVFP4 GGUF, embedded MTP, 262144 ctx on one 24 GB card, 50.44 tok/s. Recipe: piszczek.pl/blog/qwen38-27b-256k-50-tps-24gb-gpu
Michał Piszczek
cdiamond
AI & ML interests
CTO of Archdesk · Founder: Lextron.ai, Inclify, Rejsomat.pl, Robotero · Autonomous AI agents · AI reliability · Software architecture · ConstructionTech · Proof-Adjusted Autonomy · Joule Wars
Recent Activity
liked a model 5 days ago
Qwen/Qwen3.8-Flash-Next updated a dataset 6 days ago
cdiamond/ai-infrastructure-economics-glossary