Aeon Forge's picture

Aeon Forge

AEON-7

·

AI & ML interests

Systems engineer. Security researcher. Quiet architect of things that probably shouldn't work — but do. Small models doing big things. Quantization, fine-tuning, skill training, agentic workflows, and generative CAD. Been at neural nets since 2013, still surprised weekly. The GPU hums, the coffee's on, and the door's open.

Recent Activity

updated a model 1 day ago

AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-NVFP4-staging

published a model 1 day ago

AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-NVFP4-staging

updated a model 1 day ago

AEON-7/Nemotron-3-Nano-Omni-AEON-Ultimate-Uncensored-BF16

View all activity

Organizations

None yet

New activity in AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-NVFP4 1 day ago

output is garbled and nonsensical

#1 opened 2 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 3 days ago

100 tok/s rtx 5090

#4 opened 8 days ago by

New activity in AEON-7/Gemma-4-26B-A4B-it-Uncensored-NVFP4 3 days ago

This model is not uncensored at all

#2 opened 7 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 10 days ago

Benchmarks and Chain of Thought

#8 opened 16 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 10 days ago

Issue with Agentic Coding / Tool Calling - Model Hangs

#2 opened 22 days ago by

New activity in AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4 10 days ago

Image crash

#1 opened about 1 month ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 19 days ago

Feedback: Incredible project for Blackwell (ASUS GX10)

#3 opened 20 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP 19 days ago

CUDA Graph capture failed

#1 opened 22 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 23 days ago

The DGX Spark didn't reach the benchmark speed.

#5 opened about 1 month ago by

New activity in AEON-7/Gemma-4-26B-A4B-it-Uncensored-NVFP4 24 days ago

FP8 abliterated variant on the roadmap?

#1 opened 25 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 27 days ago

Using RTX 5090

#3 opened about 1 month ago by

[Request] modelopt NVFP4 + MTP variant with proper SSM layer preservation

#4 opened about 1 month ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 about 1 month ago

Is MTP possible?

#2 opened about 1 month ago by

MTP Grafted back in, findings...

#6 opened about 1 month ago by

Spliting .safetensors files into smaller pieces?

#7 opened about 1 month ago by

[Request] Pre-Tokenizer Info

#5 opened about 1 month ago by

ZuulTheMerovingian

Add a `quant_config` block (or rename the repo) so bf16 vs NVFP4 isn't ambiguous

#4 opened about 1 month ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 about 1 month ago

Speed is not fast

#2 opened about 1 month ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 about 1 month ago

gguf please

#1 opened about 1 month ago by

The BPE pre-tokenizer was not recognized!

#3 opened about 1 month ago by