🔄 In a Training Loop

Gheorghe Chesler PRO

nightmedia

·

https://www.linkedin.com/in/gchesler/

AI & ML interests

Nightmedia: human-Like AI and the MLX Deckard(qx) Formula Donations are appreciated: BTC:36d7U1n3MFaXgnNRAaEL3Pa3Hy6oFhM7XY

Recent Activity

updated a model about 8 hours ago

nightmedia/Qwen3.5-9B-Brainwaves-X-q6-hi-mlx

reacted to DavidAU's post with ❤️ about 9 hours ago

Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI A specialized fine tune with the core goal to improve instruction following and nuance, combined with the firepower of Turbo Brilliance V2 50X AGI, featuring 21 dynamically generated AGI constructs. This system pushes SOTA Qwen 3.8 fine tuned to the absolute limit, while at the same time drastically reducing tokens usage and improving quality. Examples, with detailed usage/use cases at the repo. But it is also simple: Download a quant, type "help" in the chat -> and the interactive systems will work with you to handle any use case(s) with Turbo Brilliance. This example ("fusion") is particularly potent and showcases an AGI construct using the "Elon Musk" and "Marie Curie" AI constructs: "{REASON:agi-musk-curie} Invent fusion (not fission) reactor and/or technology to make it possible." Full example at the repo ; with a lot more. https://huggingface.co/DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF PS: We are ready for Qwen 4 27B / NEXT ... and so is Turbo Brilliance V2 AGI. PS2: TWO 40B Qwen 3.8 versions with Turbo Brilliance V2 AGI are dropping this week too.

published a model about 17 hours ago

nightmedia/Qwen3.5-9B-Brainwaves-X-q6-hi-mlx

View all activity

Organizations

nightmedia 's models 504

nightmedia/gemma-4-12B-coder-fable5-composer2.5-v1-mxfp8-mlx

Any-to-Any • 12B • Updated Jun 22 • 50 • 1

nightmedia/gemma-4-12B-it-mxfp8-mlx

Any-to-Any • 12B • Updated Jun 22 • 16

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-mxfp4-mlx

Image-Text-to-Text • 9B • Updated Jun 21 • 137

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-mxfp8-mlx

Image-Text-to-Text • 9B • Updated Jun 21 • 51

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-qx86-hi-mlx

Image-Text-to-Text • 9B • Updated Jun 21 • 190 • 4

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris

Image-Text-to-Text • 10B • Updated Jun 21

nightmedia/Qwen3.6-27B-Architect-Polaris-Fable-qx64-hi-mlx

Image-Text-to-Text • 27B • Updated Jun 19 • 25 • 1

nightmedia/Qwen3.6-35B-A3B-Qwable-Holo3-Qwopus-qx64-hi-mlx

Image-Text-to-Text • 35B • Updated Jun 18 • 27 • 2

nightmedia/Qwen3.6-35B-A3B-Qwable-Holo3-Qwopus

Image-Text-to-Text • 35B • Updated Jun 18 • 121 • • 6

nightmedia/Qwen3.6-28B-PKD-Darwin-qx86-hi-mlx

Image-Text-to-Text • 27B • Updated Jun 16 • 23 • 4

nightmedia/granite-4.1-8B-Brainstone-PKD-TNG-Coder-Heretic-qx86-hi-mlx

Text Generation • 9B • Updated Jun 15 • 196 • 3

nightmedia/granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16

Text Generation • 8B • Updated Jun 15 • 134 • 2

nightmedia/granite-4.1-8B-TNG-Coder-V11-3000-Heretic-qx86-hi-mlx

Text Generation • 8B • Updated Jun 15 • 33

nightmedia/granite-4.1-8B-TNG-Coder-V11-3000-Heretic-BF16

Text Generation • 8B • Updated Jun 15 • 29

nightmedia/granite-4.1-3B-TNG-Holodeck-V2B-Heretic-q8-hi-mlx

Text Generation • 3B • Updated Jun 4 • 10

nightmedia/granite-4.1-8B-Holodeck-q8-hi-mlx

Text Generation • 9B • Updated Jun 1 • 11

nightmedia/granite-4.1-3B-TNG-Claude-Coder-xLAM-Heretic-q8-hi-mlx

Text Generation • 3B • Updated Jun 1 • 67

nightmedia/granite-4.1-3B-TNG-Agent-Haskell-Python-Golang-Claude-Heretic-q8-hi-mlx

Text Generation • 3B • Updated May 31 • 188 • 2

nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-qx86-hi-mlx

Image-Text-to-Text • 35B • Updated May 31 • 32 • 3

nightmedia/granite-4.1-3B-Agent3-q8-hi-mlx

Text Generation • 3B • Updated May 28 • 45 • 1

nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx

Image-Text-to-Text • 35B • Updated May 26 • 484 • 5

nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-qx64-hi-mlx

Image-Text-to-Text • 35B • Updated May 26 • 22

nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-mxfp4-mlx

Image-Text-to-Text • 35B • Updated May 26 • 29

nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-BF16

Image-Text-to-Text • 35B • Updated May 26 • 40 • 2

nightmedia/Qwen3.5-9B-Claude-Deckard-Agent-Coder-Heretic-qx86-hi-mlx

Image-Text-to-Text • 9B • Updated May 21 • 895 • 11

nightmedia/NVIDIA-Nemotron-Labs-3-Elastic-12B-A2B-GGUF

Text Generation • 12B • Updated May 21 • 89 • 2

nightmedia/Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-BF16

Image-Text-to-Text • 9B • Updated May 20 • 65 • 2

nightmedia/Qwen3.5-9B-SanchoPanza-qx86-hi-mlx

Image-Text-to-Text • 9B • Updated May 19 • 9

nightmedia/Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-dwq4-mlx

Text Generation • 9B • Updated May 19 • 172 • 2

nightmedia/gemma-4-E2B-Deckard-ShiningValiant3-q8-hi-mlx

Any-to-Any • 5B • Updated May 16 • 20 • 1