😀 ... it's amazing!

Schestex

Schestex

·

Xtravaganz

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF:NInfer results on RTX PRO 4000 Blackwell SSF and Non-SSF any interest in experimenting with NInfer builds?

new activity 3 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B:New Model based on Qwen 3.8

new activity 3 days ago

DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1:VERSION / QUANT: NVFP4 NInfer / Blackwell build of Cold-Fusion V1.1 / Blackwell Pro 4000

View all activity

Organizations

None yet

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 3 days ago

NInfer results on RTX PRO 4000 Blackwell SSF and Non-SSF any interest in experimenting with NInfer builds?

#6 opened 19 days ago by

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 3 days ago

New Model based on Qwen 3.8

#23 opened about 2 months ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 3 days ago

VERSION / QUANT: NVFP4 NInfer / Blackwell build of Cold-Fusion V1.1 / Blackwell Pro 4000

#18 opened 10 days ago by

New activity in Schestex/Qwen3.8-27B-ColdFusion-NVFP4-NInfer 4 days ago

MTP Hybrid-A1 Controlled OLD W8-MTP vs Hybrid-A1 benchmarks

#1 opened 10 days ago by

New activity in neroued/Qwen3.8-27B-nvfp4-NInfer 9 days ago

24 GB optimized NVFP4 NInfer artifact

#7 opened 15 days ago by

New activity in Ostfralla/Qwen3.8-27B-NVFP4-NInfer 11 days ago

How does this compare to neroued/Qwen3.8-27B-nvfp4-NInfer?

#3 opened about 1 month ago by

New activity in peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF 19 days ago

nInfer version

#11 opened 29 days ago by

New activity in cometkim/Qwen3.8-27B-nvfp4full-NInfer 19 days ago

Blackwell Pro 4000 SFF / non SFF Prefill and MTP 3-5 Results Text / Code

#1 opened 19 days ago by

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 19 days ago

Would you consider GSQ-RCO IQ3_S + MTP for a Qwen3.8-27B coding-focused fine-tune?

#8 opened 20 days ago by

New activity in peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF 20 days ago

Worth validating GSQ-RCO IQ3_S against UD-IQ3_S on Dirk?

#16 opened 20 days ago by

NVFP4-MTP build available for each model type?

#4 opened about 1 month ago by

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF 21 days ago

This model is COOKING HARD

#10 opened 23 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 21 days ago

GSQ-RCO IQ3_S + MTP for NEO-CODER-MAX?

#8 opened 21 days ago by

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 21 days ago

Idea: Combining your agentic iMatrix calibration with GSQ/RCO.

#5 opened 21 days ago by

MTP VS DFlash2

#3 opened 26 days ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF 24 days ago

Have you considered creating a variant of Dflash2? This typically offers higher inference speed

#27 opened 27 days ago by

New activity in cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 30 days ago

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

#1 opened about 1 month ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF about 1 month ago

VERSION NVFP4 : Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NVFP4

#13 opened about 1 month ago by

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF about 1 month ago

Qwen3.8-27B as ThinkingCap with MTP!

#10 opened about 1 month ago by

New activity in sakamakismile/ThinkingCap-Qwen3.6-27B-NVFP4 about 2 months ago

Qwen3.6-27B-NVFP4-XS

#1 opened about 2 months ago by