README.md

---
license: apache-2.0
language:
- en
pipeline_tag: any-to-any
library_name: transformers
tags:
- sponsor
- buy me a coffee
- projects
- help
- support
- contact
- partners
- ggufs
- moes
- mixture of experts
- source
- custom
- models by sort
- FAQs
- help docs
- SOTA models
- about us
- Turbo Brilliance Systems
- NEO Imatrix
- source code
- Brainstorm Adapter
- Cold Fusion Training
- Model merging
- model tuning
- unsloth
- mergekit
- llamacpp
---

<h2>SUPPORT / HELP / SPONSOR / PROJECTS / PREMIUM / SORT Models (multi) / FAQs</h2>

<img src="valhalla.webp" style="float:right; width:300px; height:300px; padding:10px;">

To support our team, sponsor, "Buy Me A Coffee", commission project(s), access premium item(s)/model(s)/module(s), model modifications, GET HELP, 
see a sorted list of models (380+) and more please see below.

We build precision models at scale for the community.

We are user-funded, and use local hardware to create, tune and deploy models worldwide.

We also create systems for fine tuning, and specialized model systems too as well as "augment" current model/AI technology.

That includes:
- Model fine tuning across a diverse arch type of models and sizes, including MOEs/sparse moes. (over 1000)
- Model merging (and also fine tuning) (over 2700)
- Model expansion/contraction (27B-> 40B ; 27B to 21B, 13B... and so on => both "dense" and "moe models")
- Cold Fusion Training Technology for model fine tuning.
- Brainstorm Universal model adapter to improve intelligence and creativity.
- Turbo Brilliance => A universal model generation, IQ, and token reduction / enhancement technology.
- NEO Imatrix dataset => Strongest Imatrix dataset ever built.

Some models took hours to tune, whereas others took days to weeks including the countless hours of testing; especially for our SOTA models.

If you would like to sponsor our work the "Buy Me a Coffee" system was just added as per multiple requests and the fact is we can do a lot more, we just need the equipment to do it:

https://buymeacoffee.com/davidbelton

Thank you in advance.

<b>ABOUT DavidAU:</B>
- As of this writing my repo (DavidAU) has over 4 million downloads per month. This does not account for "user setup repos" / mirrors of my teams models.
- I have published over 2000 models over the past 3 years - Llama, Qwen, Mistral, LFM, OpenAI, GLM, Gemmas and many others. (see details below)
- After surpassing 10,000 followers on Huggingface, it is now time to take things to the next level.
- The journey is just getting underway...
- PS: about "actual me"... see below.

<B>Our latest project(s) (MAJOR) is here (names subject to change):</B>

- https://huggingface.co/DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
- https://huggingface.co/DavidAU/Qwen3.8-27B-UltimateDetails2-stage1__The-Harley-Pelican
- MOST RECENT MODELS: https://huggingface.co/DavidAU/models?sort=created

<B>Contact / About Me - David Belton:</B>
- I am a master software engineer with 45 years of experience (programming in machine code since age 11) and 30+ years of business experience.
- I have been experimenting, merging and tuning models now for close to 4 years.
- I don't worry about if it is impossible, I get it done.
- REPO (380+ models): https://huggingface.co/DavidAU
- COLLECTIONS (38): https://huggingface.co/DavidAU/collections
- LinkedIN: https://www.linkedin.com/in/david-belton-5855b6370/
- Contact me on Discord (or VIA LinkedIN above): David_AU [drawless111]

<B>Main partner "in crime" is "nightmedia":</B>
- REPO: https://huggingface.co/nightmedia
- COLLECTIONS: https://huggingface.co/nightmedia/collections
- LinkedIN: https://www.linkedin.com/in/gchesler/

<img src="free-mind.gif" style="padding:0px;">

<B>Here are some of the (380+ :: Number was 1500 at one point, but cut due to HGF storage limits) strongest models so far:</B>

NOTE: I generate source and GGUF quants, for many of my models, the community has generated additional quant types/variations like MLX, NVFP4, and so on... you will
find these quants in the "community" tab at the repo and/or under "Quantizations" on the main repo page.

BY SORT - GENERAL:
- Most Likes: https://huggingface.co/DavidAU/models?sort=likes
- Most Downloads: https://huggingface.co/DavidAU/models?sort=downloads
- Least parameters: https://huggingface.co/DavidAU/models?sort=least_params
- Most parameters: https://huggingface.co/DavidAU/models?sort=most_params
- Trending on Hugging Face: https://huggingface.co/models?sort=trending&search=DavidAU
- Trending on Hugging Face + Inference available (try it in your browser): https://huggingface.co/models?inference_provider=all&sort=trending&search=DavidAU

ADVANCED SORT:

Start with:
- https://huggingface.co/models?sort=trending&search=DavidAU
- then enter model / size / name etc separated (each) by a SPACE ; this is far stronger than the "repo" only search (single keyword)

BY SORT - MOEs/Sparse MOES:
- In house created, MOES: https://huggingface.co/DavidAU/models?search=moe 
- Sparse MOES (4b) IE Gemma and others: https://huggingface.co/DavidAU/models?search=-a4
- Sparse MOES (3b) IE Qwen: https://huggingface.co/DavidAU/models?search=-a3
- Sparse MOES (1b) IE LFM/smaller MOES: https://huggingface.co/DavidAU/models?search=-a1

By SORT - SIZE (there will be other sizes/oddball sizes too):
- 1B : https://huggingface.co/DavidAU/models?search=1b
- 3B : https://huggingface.co/DavidAU/models?search=3b
- 8B : https://huggingface.co/DavidAU/models?search=8b
- 9B : https://huggingface.co/DavidAU/models?search=9b
- 12B : https://huggingface.co/DavidAU/models?search=12b
- 13B : https://huggingface.co/DavidAU/models?search=13b
- 24B : https://huggingface.co/DavidAU/models?search=24b
- 27B : https://huggingface.co/DavidAU/models?search=27b
- 40B : https://huggingface.co/DavidAU/models?search=40b

BY SORT - MODEL:
- QWENS: https://huggingface.co/DavidAU/models?sort=downloads&search=qwen
- GEMMAS: https://huggingface.co/DavidAU/models?sort=downloads&search=gemma
- LFMS: https://huggingface.co/DavidAU/models?sort=downloads&search=lfm
- LLAMA: https://huggingface.co/DavidAU/models?sort=downloads&search=llama
- LLAMA 3,3.1,3.2,3.3: https://huggingface.co/DavidAU/models?search=l3
- MISTRAL: https://huggingface.co/DavidAU/models?sort=downloads&search=mistral
- GLM: https://huggingface.co/DavidAU/models?sort=downloads&search=glm
- OPENAI/GPT-OSS: https://huggingface.co/DavidAU/models?sort=downloads&search=gpt
- "Horror": https://huggingface.co/DavidAU/models?search=horror&sort=likes

Special note - "Out of print" models:
- A number of my models no longer are listed at my repo due to storage limits. You can however find them at other repos at HGF using: https://huggingface.co/search/full-text?q=davidau&type=model
- I also keep local backups where possible.

<h2>SOTA MODELS By My Team:</h2>

<img src="cannonball.webp" style="padding:0px;">

NOTE: Most models have benchmarks, and 3rd party benchmarks (at repo or in the community section)

Qwen3.6 27B: The strongest, overall qwen ever beating all other Qwens in total operational power with over 2400 likes // 4 million+ total downloads
and has over 70 additional repos with additional quant types:
- https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
- Benchmarks (spoiler: It beats everyone): https://blog.robai.net/27bevals/ 

Qwen3.8 27B: The highest scoring Qwen in brute, raw intelligence, using Qwen 3.8's 3 new reasoning modes, plus token reduction (1/2 to 1/10) enhancements
and over 1600 likes + and 100+ additional quant repos:
- https://huggingface.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

Qwen3.8 27B: Super smart and 1/2 to 1/20 the reasoning tokens AND 5 reasoning/5 instruct modes switchable on the fly (even in chat):
- https://huggingface.co/DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

Qwen3.8 27B: 99% power of BF 16 at 4 and 8 bit. Power, Control and NO DE censoring for ultimate performance also with reasoning token reductions:
- https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF

Qwen3.6 40B: The 40B Monster, specializing in creative and research with 730+ likes and over 2 million downloads:
- https://huggingface.co/DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF

Qwen3.5 9B: At just 9B parameters it beats most untuned 27B models in both intelligence (640 ARC-C) and performance, over 1000 likes, plus features 5 reasoning and 5 instruct modes (Qwen 3.8) too:
- https://huggingface.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
- This is our office workhorse ; bullet proof, stable, fast and off the scale IQ to boot.

<B>For model specific issues/help/FAQ see:</B>
- https://huggingface.co/DavidAU
- Search for your model.
- Check the model repo page AND community section.
- FAQS for all models: https://huggingface.co/collections/DavidAU/davids-software-docs-and-how-to-for-models

<B>Support our team, sponsor, "Buy Me A Coffee":</B>
- https://buymeacoffee.com/davidbelton

<B>Commission project(s):</B>
- coming soon.

<B>Access premium item(s)/model(s)/module(s):</B>
- coming soon.

<B>Model Modifications:</B>
- coming soon.

<B>ALL OTHER INQUIRES:</B>
- Open a discussion in the community tab at this repo.