David Belton's picture

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 13 hours ago

DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF:Source

new activity about 13 hours ago

DavidAU/Qwen3.5-46B-A3B-HighIQ-Prototype-II:Request

new activity about 13 hours ago

DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF:Hoping someone can finally help me with this

View all activity

Organizations

New activity in DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF about 13 hours ago

Source

#1 opened about 16 hours ago by

New activity in DavidAU/Qwen3.5-46B-A3B-HighIQ-Prototype-II about 13 hours ago

Request

#1 opened 1 day ago by

HuggingFace007Galeiq

New activity in DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF about 13 hours ago

Hoping someone can finally help me with this

#8 opened 5 days ago by

updated a model about 14 hours ago

DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF

Image-Text-to-Text • 27B • Updated about 13 hours ago • 6.24k • 13

posted an update 1 day ago

Post

505

Qwen3.6 27B - NEO-Code Imatrix Max GGUF Quants [exceeds Unsloth in key metrics]:

All quants benchmarked with 5 key metrics.
A DAVIDAU vs UNSLOTH Metrics showdown.
Quant quality exceeds Unsloth in key metrics.
IQ2_M to Q6 available.
Standout: IQ4XS at 94% of BF16 precision.
Full explainer for Quant metrics.

DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF

1 reply

·

updated a model 1 day ago

DavidAU/Qwen3.5-35B-A3B-HighIQ-Prototype-II

Image-Text-to-Text • 36B • Updated 1 day ago • 18 • 1

updated 5 collections 1 day ago

Qwen3 - 30B-A3B (128 experts) and higher

Versions of Qwen3's 30B MOE - Mixture of Experts 128 - in NEO, Horror, and Brainstorm configs from 30B up to 55B. • 24 items • Updated 1 day ago • 6

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 41 items • Updated 1 day ago • 41

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on. • 278 items • Updated 1 day ago • 679

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 70 items • Updated 1 day ago • 28

Thinking / Reasoning Models - Reg and MOEs.

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 123 items • Updated 1 day ago • 21

updated a model 1 day ago

DavidAU/Qwen3.5-46B-A3B-HighIQ-Prototype-II

Image-Text-to-Text • 46B • Updated 1 day ago

updated 5 collections 1 day ago

Thinking / Reasoning Models - Reg and MOEs.

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 123 items • Updated 1 day ago • 21

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 41 items • Updated 1 day ago • 41

Qwen 3 - Horror / Neo Imatrix / Max Qs / 32-256k ctx

Qwen3s: 0.6B, 1.7B, 4B, 8B, 14B, 30B (MOE), 32B using Neo / Horror / Other imatrix datasets, exp methods, and ways to improve reasoning/output gen. • 17 items • Updated 1 day ago • 5

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 70 items • Updated 1 day ago • 28

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on. • 278 items • Updated 1 day ago • 679

published a model 1 day ago

DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF

Image-Text-to-Text • 27B • Updated about 13 hours ago • 6.24k • 13

liked a model 1 day ago

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated about 13 hours ago • 162k • 727

New activity in DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking 1 day ago

Getting lotsa star trek...

#2 opened 13 days ago by