🔄 In a Training Loop

David Belton PRO

DavidAU

·

AI & ML interests

Application(s) of single/multiple LLMs in specialized use cases & automation tasks. LLM, Prompt , System Role and Parameter engineering VIA chat / API. 2700+ merge models, over 600 fine tunes, over 1000 models published. DISCORD: David_AU [drawless111]

Recent Activity

new activity about 11 hours ago

DavidAU/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF:What model ?

new activity about 12 hours ago

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Seeking cooperation

new activity about 12 hours ago

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Clean Up the README

View all activity

Organizations

New activity in DavidAU/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 11 hours ago

What model ?

#5 opened about 11 hours ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 12 hours ago

Seeking cooperation

#20 opened 6 days ago by

Clean Up the README

#26 opened 5 days ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF about 17 hours ago

Can this technique be applied to Qwen 3.8 Flash Next?

#30 opened 6 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 18 hours ago

Russian language degradation

#38 opened 1 day ago by

New activity in DavidAU/Qwen3.5-9B-Cold-Fusion-GAIN-v1.0-Uncensored-Heretic-NEO-MAX-Imatrix-GGUF 1 day ago

mmproj-BF16 seem broken

#6 opened 2 days ago by

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

It starts very good but loops afterwards

#37 opened 1 day ago by

New activity in DavidAU/Qwen3.8-27B-THE-BIG-BANG-Cold-Fusion-709 1 day ago

Pelican Test - Q4ks, non imatrix, rplus3 branch

#3 opened 4 days ago by

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

We benched 20+ local models on a 320-tool agent harness — DavidAU's TURBO-Fable-735 (27B) matches our all-time champion at 1/40th the thinking tokens

#36 opened 2 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 2 days ago

Amazing Work here

#35 opened 2 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 3 days ago

It's getting stuck in a loop in my coding agent

#33 opened 4 days ago by

Pelican Tests, Turbo, quants and V2/V3 + Pelican on a Harley [v3]

#29 opened 4 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 3 days ago

Can't load the model in Unsloth Desktop

#20 opened 3 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 3 days ago

Very effective

#21 opened 6 days ago by

New activity in DavidAU/Qwen3.8-27B-THE-BIG-BANG-Cold-Fusion-709 4 days ago

Pelican Test - q4ks, 4 bit, non Imatrix

#2 opened 4 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 4 days ago

Downloading now ...

#3 opened 7 days ago by

Request for MLX-compatible version / conversion help for the new model

#31 opened 4 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 4 days ago

Can you make a dflash2-draft-model for the main-model？

#16 opened 5 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 4 days ago

Will there be a LOW MTP version too?

#4 opened 7 days ago by

Conversations/thinking not showing properly

#30 opened 4 days ago by