Michał Piszczek

cdiamond

·

https://piszczek.pl

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

repliedto Avifenesh's post 1 day ago

Wrote this up because it still feels backwards. Acceptance dropped, tok/s went up. Full draft head: 66.7% / 117.1 tok/s. Trimmed: 63.6% / 121.7. Later remeasure +5.1% on a Pro 6000, +6.4% on a 5090 laptop. Full head still accepts more. Loses anyway. Not my idea. FR-Spec. I just wired it for the native MTP head. https://huggingface.co/blog/Avifenesh/masked-mtp-drafts https://huggingface.co/Avifenesh/Qwen3.8-27B-NVFP4-MTP-GGUF

new activity 1 day ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF:Why the NVFP4 MTP head beats a higher precision one (measured)

updated a collection 1 day ago

Qwen3.8 27B at 256K on 24 GB

View all activity

Organizations

replied to Avifenesh's post 1 day ago

Seen the same thing from the quantization side. My Qwen3.8 27B GGUF keeps the MTP head in native NVFP4 on purpose. Upgrading the head to Q5_K/Q6_K (+69 MiB) looked like a free win and instead acceptance went 48.3% to 33.1% and throughput dropped 26.6%. The head only has to agree with the quantized target, not with the BF16 parent, so trimming and quantizing probably win for the same reason. Full numbers: https://piszczek.pl/blog/qwen38-27b-256k-50-tps-24gb-gpu

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 1 day ago

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

#1 opened 1 day ago by

updated a collection 1 day ago

Qwen3.8 27B at 256K on 24 GB

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 • 6 items • Updated 1 day ago

liked a model 1 day ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated 1 day ago • 859 • 4

updated a model 1 day ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated 1 day ago • 859 • 4

published a model 1 day ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated 1 day ago • 859 • 4

liked a model 6 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 5 days ago • 1.01M • • 11.3k

updated a Space 16 days ago

Ai Economics Tools

12 free calculators for AI cost, energy and agent verificati

published a Space 16 days ago

Ai Economics Tools

12 free calculators for AI cost, energy and agent verificati

updated a dataset 16 days ago

cdiamond/proof-adjusted-autonomy-examples

Viewer • Updated 16 days ago • 12 • 65

updated a dataset 18 days ago

cdiamond/ai-economics-formulas

Viewer • Updated 18 days ago • 12 • 48

published a dataset 18 days ago

cdiamond/ai-economics-formulas

Viewer • Updated 18 days ago • 12 • 48

updated a dataset 19 days ago

cdiamond/ai-infrastructure-economics-glossary

Viewer • Updated 19 days ago • 12 • 98 • 1

liked a dataset 29 days ago

cdiamond/ai-infrastructure-economics-glossary

Viewer • Updated 19 days ago • 12 • 98 • 1

published a dataset 29 days ago

cdiamond/proof-adjusted-autonomy-examples

Viewer • Updated 16 days ago • 12 • 65