DavidAU/DeepSeek-MOE-4X8B-R1-Distill-Llama-3.1-Deep-Thinker-Uncensored-24B-GGUF

Text Generation • Updated Mar 3 • 1.15k • 11

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-gguf

Text Generation • Updated Mar 3 • 260 • 6

Note MOE - Mixture of Experts version. This model has 8 times the power of a standard 3B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/Qwen2.5-MOE-6x1.5B-DeepSeek-Reasoning-e32-8.71B-gguf

Text Generation • Updated Mar 5 • 252 • 5

Note MOE - Mixture of Experts version. This model has 6 times the power of a standard 1.5B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/DeepSeek-MOE-4X8B-R1-Distill-Llama-3.1-Mad-Scientist-24B-GGUF

Text Generation • Updated Mar 3 • 289 • 3

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-gguf

Text Generation • Updated Mar 6 • 1.31k • 4

Note MOE - Mixture of Experts version. This model has 2 times the power of a standard 1.5B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-gguf

Text Generation • Updated Mar 6 • 731 • 4

Note MOE - Mixture of Experts version. This model has 2 times the power of a standard 7B model. It will have deeper thinking/reasoning and more complex prose.

DavidAU/Deep-Reasoning-Llama-3.2-10pack-f16-gguf

Text Generation • Updated Mar 3 • 2.26k • 1

Note Links to all 10 models in GGUF (regular and Imatrix) format also on this page.

DavidAU/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B

Text Generation • Updated Apr 4 • 462

Note MOE - Mixture of Experts version. This model has 6 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose. Links to GGUF / Imatrix GGufs also on this page.

DavidAU/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-GGUF

Text Generation • Updated Apr 4 • 1.8k

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose.

mradermacher/L3.1-MOE-4X8B-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-e32-25B-i1-GGUF

Updated Apr 4 • 2.25k • 1

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose. Imatrix GGUF Quant version of my model by Team "mradermacher".

DavidAU/L3.1-MOE-4X8B-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-e32-25B-GGUF

Text Generation • Updated Apr 4 • 317

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose.

mradermacher/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-i1-GGUF

Updated Apr 4 • 967

Note MOE - Mixture of Experts version. This model has 4 times the power of a standard 8B model. It will have deeper thinking/reasoning and more complex prose. Imatrix GGUF Quant version of my model by Team "mradermacher".

mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF

Updated Apr 2 • 4.02k • 2

Note Imatrix GGUF Quant version of my model by Team "mradermacher".

mradermacher/L3.1-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF

Updated Apr 2 • 563 • 1

Note Imatrix GGUF Quant version of my model by Team "mradermacher".

DavidAU/L3.1-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-8B

Text Generation • Updated Apr 4 • 8 • 1

Note Links to GGUF / Imatrix GGufs also on this page.

DavidAU/L3.1-Dark-Reasoning-Jamet-8B-MK.I-Hermes-R1-Uncensored-8B

Text Generation • Updated Apr 4 • 23 • 1

Note Links to GGUF / Imatrix GGufs also on this page.

DavidAU/L3.1-Dark-Reasoning-Anjir-Hermes-R1-Uncensored-8B

Text Generation • Updated Apr 4 • 22 • 1

Note Links to GGUF / Imatrix GGufs also on this page.

DavidAU/L3.1-Dark-Reasoning-Celeste-V1.2-Hermes-R1-Uncensored-8B

Text Generation • Updated Apr 4 • 22 • 1

Note Links to GGUF / Imatrix GGufs also on this page.

DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters

Updated Apr 4 • 113

Note Document detailing all parameters, settings, samplers and advanced samplers to use not only my models to their maximum potential - but all models (and quants) online (regardless of the repo) to their maximum potential. Included quick start and detailed notes, include AI / LLM apps and other critical information and references too. A must read if you are using any AI/LLM right now.

DavidAU/AI_Autocorrect__Auto-Creative-Enhancement__Auto-Low-Quant-Optimization__gguf-exl2-hqq-SOFTWARE

Text Generation • Updated Mar 10 • 46

Note SOFTWARE patch (by me) for Silly Tavern (front end to connect to multiple AI apps / connect to AIs- like Koboldcpp, Lmstudio, Text Gen Web UI and other APIs) to control and improve output generation of ANY AI model. Also designed to control/wrangle some of my more "creative" models and make them perform perfectly with little to no parameter/samplers adjustments too.