🔄 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

updated a model about 4 hours ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored

new activity about 5 hours ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF:First tests are good for now ( use of model for SillyTavern RP )

new activity about 5 hours ago

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Error The selected model was loaded with a context length that is too small for this request.

View all activity

Organizations

updated a model about 4 hours ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored

Image-Text-to-Text • 28B • Updated about 4 hours ago • 78 • 44

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 5 hours ago

First tests are good for now ( use of model for SillyTavern RP )

👍❤️ 1

#8 opened about 15 hours ago by

Gastberend

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 5 hours ago

Error The selected model was loaded with a context length that is too small for this request.

#48 opened 1 day ago by

Merdo2121

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 5 hours ago

Tips and Troubleshooting / Fixes // getting max performance // etc etc.

🔥👍 6

#4 opened about 23 hours ago by

DavidAU

Ready to put stage 2 to the test.

#2 opened 1 day ago by

dwbrott

Immediatly ready to try ... downloading...

👍❤️ 1

#3 opened 1 day ago by

donboyle

[BUG] INSTRUCT mode stops suddenly: does not call tools in multi-turn agent loops

#5 opened about 22 hours ago by

BebopVox

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 19 hours ago by

47Hunter47

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored about 5 hours ago

Tips and Troubleshooting / Fixes // getting max performance // etc etc.

#11 opened about 5 hours ago by

DavidAU

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

👀🔥 1

#10 opened about 5 hours ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 5 hours ago

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

🚀🔥 3

#10 opened about 5 hours ago by

DavidAU

updated a model about 5 hours ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

Image-Text-to-Text • 27B • Updated about 4 hours ago • 4.9k • 45

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored about 24 hours ago

SUPER Pelicans - in both Thinking and Instruct ,

😎 2

#6 opened 2 days ago by

DavidAU

posted an update 1 day ago

Post

3850

Qwen 3.8 27B - TWIN TURBO, Fable Fusion (10 modes of operation)

Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit AND THIS is instruct mode - thinking/reasoning is higher.

This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.

This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants.

BUT WE WENT FURTHER:

Now with 5 reasoning modes (2 new - UltraXhigh / Einstein), and 5 instruct modes (2 new - UltraXhigh / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level).

GGUFS:

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

SOURCE:

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored