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

new activity 10 days ago

AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16:Vision Tower option?

updated a model 11 days ago

AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXED

updated a model 13 days ago

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter

View all activity

Organizations

None yet

New activity in AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 10 days ago

Vision Tower option?

#6 opened 23 days ago by

New activity in AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXED 14 days ago

Great work

#1 opened 21 days ago by

New activity in AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 27 days ago

Feature Request / Architecture Synthesis for Qwen3.8 27B GA Cut: Validating Low-Distortion Rank-1 Abliteration under Real-World High-Entropy Inference

#5 opened 29 days ago by

New activity in AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 about 1 month ago

Suggest optimizing for agent tool calling scenarios

#3 opened about 1 month ago by

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

waiting for Aeon-qwen 3.8 27b -Ultimate-bf16

#10 opened about 2 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 2 months ago

RTX 5090 numbers for the hardware compatibility matrix

#10 opened 2 months ago by

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 2 months ago

RTX 5090

#3 opened 3 months ago by

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4 2 months ago

Thinking loop

#3 opened 3 months ago by

coe-arrtificial

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 2 months ago

Issue with Agentic Coding / Tool Calling - Model Hangs

#2 opened 5 months ago by

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 3 months ago

It may generate garbled characters.

#2 opened 3 months ago by

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4 3 months ago

Not actually abliterated - avoid this model

#2 opened 3 months ago by

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 3 months ago

Solid work — testing for mobile deployment

#1 opened 3 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 3 months ago

The first uncensored that's actually good

#8 opened 4 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 4 months ago

Benchmarks not useful for real world usage

#6 opened 4 months ago by

Error with aeon-vllm-ultimate:latest on dgx spark

#5 opened 4 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 4 months ago

is it possible to apply --kv-cache-dtype fp8

#6 opened 4 months ago by

Kudos — combined your model with DFlash/AEON for GB10

#7 opened 4 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS 4 months ago

100 tok/s rtx 5090

#4 opened 4 months ago by

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

This model is not uncensored at all

#2 opened 4 months ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 4 months ago

Benchmarks and Chain of Thought

#8 opened 4 months ago by