Mert Özkan

47Hunter47

·

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF:would you make a finetune or finetunes for qwen3.8 flash next?i mean unscenswored and think less, since suffers same flaws as 3.8 27B

new activity 5 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:RTX 5090 32GB VRAM 128GB VRAM test results

new activity 5 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_XXS 23tps on ASUS Z13 64GB RAM (AMD Ryzen™ AI MAX+ 395)

View all activity

Organizations

None yet

New activity in DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF 3 days ago

would you make a finetune or finetunes for qwen3.8 flash next?i mean unscenswored and think less, since suffers same flaws as 3.8 27B

#7 opened 8 days ago by

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 5 days ago

RTX 5090 32GB VRAM 128GB VRAM test results

#4 opened 27 days ago by

IQ3_XXS 23tps on ASUS Z13 64GB RAM (AMD Ryzen™ AI MAX+ 395)

#21 opened 21 days ago by

Speed tests on a 3060 laptop with 48GB RAM

#31 opened 14 days ago by

2vibeornot2vibe

Benchmark & Reproduction Setup: Qwen3.8-Flash-Next GSQ-RCO IQ3_XXS (24.82 t/s at full 262k context on single RTX 3090)

#33 opened 12 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 14 days ago

There has always been a problem with prematurely stopping the output.

#24 opened 16 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 26 days ago

12+12 coming soon ... Now avail - 5 reasoning modes, 5 instruct modes: New Version "TWIN TURBO" Qwen3.8 27B ; a preview of what is to come...

#45 opened about 1 month ago by

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 1 month ago

Tool / Agent / Agentic -> Corrected Jinja template for tools / agents / agentic work.

#10 opened about 1 month ago by

FIXED Jinja // Agentic/tool-calling use: mid-tool-call stream drops + premature turn ends (base Qwen3.8 is fine in the same stack)

#7 opened about 1 month ago by

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF about 1 month ago

Is this model same as Q4KM for coding related tasks?

#22 opened about 1 month ago by

Request for standard Q-type quantizations (Q3_K_XL, Q4_K_M/XL) for AMD GPU compatibility

#5 opened about 1 month ago by

myhugginfacegacc

This is amazing, now i have 250k ctx

#19 opened about 1 month ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 1 month ago

What agent are you all running this with?

#42 opened about 1 month ago by

It starts very good but loops afterwards

#37 opened about 1 month ago by

Will there be a LOW MTP version too?

#4 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

thinking loop issue

#29 opened about 1 month ago by

New activity in Qwen/Qwen3.8-Flash-Next about 2 months ago

Qwen3.8-Flash-Next (Qwen 4 - Preview) vs 3.8 27B - Architecture Teardown

#22 opened about 2 months ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU about 2 months ago

Sooo hyped!

#1 opened about 2 months ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 about 2 months ago

gguf please

#3 opened about 2 months ago by