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

new activity 9 days ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF:Between a unsloth Q3_K_XL and Q4_K_XL in terms of quantity but also speed?

liked a model 16 days ago

Qwen/Qwen3.8-Flash-Next

new activity 17 days ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF:NVFP4 without gguf possible in same size and quality for vllm?

View all activity

Organizations

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 9 days ago

Between a unsloth Q3_K_XL and Q4_K_XL in terms of quantity but also speed?

#4 opened 9 days ago by

pyrolistical

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 17 days ago

NVFP4 without gguf possible in same size and quality for vllm?

🚀 1

#2 opened 17 days ago by

gameonvinay

Why the NVFP4 MTP head beats a higher precision one (measured)

#1 opened 23 days ago by

cdiamond

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 23 days ago

Why the NVFP4 MTP head beats a higher precision one (measured)

#1 opened 23 days ago by

cdiamond

Michał Piszczek

AI & ML interests

Recent Activity

Organizations

cdiamond's activity

Between a unsloth Q3_K_XL and Q4_K_XL in terms of quantity but also speed?

NVFP4 without gguf possible in same size and quality for vllm?

Why the NVFP4 MTP head beats a higher precision one (measured)

Why the NVFP4 MTP head beats a higher precision one (measured)