AEON-7 / Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.
Why this job: topics: vllm, quantization
What it does
- Empirical literature on capability gains from abliteration
- What the lifted overhead also means
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 34 days ago
- Stars
- 492
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 95% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 47% closed
- 9 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| syv-ai / HyperQwen | 2,626 | 6 days ago | Apache-2.0 | No downloads |
| Avarok-Cybersecurity / atlas | 714 | 47 days ago | AGPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- Python 95%
- Shell 3%
- Dockerfile 2%
Topics
- abliteration
- blackwell
- dflash
- dgx-spark
- llm
- nvfp4
- quantization
- qwen
- qwen3
- speculative-decoding
- uncensored
- vllm
Project record
- JobLocal LLMs
- StatusListed
- Commits49
- Forks55
- Watching5
- Stars in 28 days+14
- CreatedApr 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026