Wondernutts/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-int4-ov

Qwen3.6-27B AEON Ultimate, OpenVINO INT4. The dense Qwen: richest prose, on ONE Intel Arc B70.

This is AEON-7's "Ultimate Uncensored" tune of the dense Qwen3.6-27B, converted to OpenVINO INT4 with Intel's published recipe for this model (int4 asymmetric, group size 128). It completes my Qwen3.6 family: pick the 35B MoE siblings for speed (~108 tok/s), pick this dense 27B when you want every token computed by the full 27B parameters: noticeably richer, more deliberate prose at dense speeds.

Runs on the stock 2026.2 runtime. No patches, no workarounds, straight out of the converter.

Family and toolkit: OpenVino-For-Gemma-4 toolkit, 35B MoE heretic, Ornith 35B MoE, plus the Gemma-4 side: 26B MoE, 31B, 12B.

Measured performance (single Arc Pro B70, OpenVINO 2026.2)

Metric	Value
Decode, short context	~32 tok/s
Decode at 6K context	~28 tok/s
Prefill (pp512)	~1,660 tok/s (no published same-card baseline for this model)
Prefill at depth	~2,100 tok/s at 2K-6K, ~1,850 at 16K (ingests 16K in ~10 s); 32K exceeds a single 32 GB card's VRAM
Model load	~32 s
Weights	~15 GB (24 GB+ card recommended for real context headroom)

Long-context capability and the honest single-card limit

Needle retrieval test: a password fact planted early in the prompt, retrieved at the end.

Context	Result
8K	PASS (6.4 s total)
16K	PASS (13.6 s)
24K	PASS (29.4 s)
32K	out of GPU memory on a 32 GB card

The dense 27B carries 64 layers of KV cache; around 32K context that plus ~15 GB of weights exceeds a 32 GB card. Practical guidance on one B70: treat this as a 24K model. The MoE siblings verify to 32K on the same card because their KV footprint leaves more headroom. The architecture itself is rated to 262K positions; more VRAM extends it.

Sample output

Asked, in character as a dry-witted housecarl, about a sweetroll dropped off a cliff:

You have the navigational instincts of a blind horse, my lord. If you had looked down for five seconds, we would still be warm and well-fed.

How to run

Identical usage to the 35B MoE sibling: standard Qwen <|im_start|> format, pre-closed <think>\n\n</think> block for fast no-think replies (remove it and give at least 1024 tokens to enable reasoning), {"DYNAMIC_QUANTIZATION_GROUP_SIZE": 0} only if you use continuous batching. Full runnable snippet on the sibling card; point it at this folder.

pip install openvino-genai==2026.2.0 huggingface_hub
huggingface-cli download Wondernutts/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-int4-ov --local-dir ./qwen36-27b-aeon-ov

Conversion recipe (reproducible)

Intel's published recipe for the dense 27B: INT4 asymmetric, group size 128, no AWQ, no ignored_scope, exported as image-text-to-text with optimum-intel (git main) and transformers 5.2.0. The finetune repo's config was saved by a newer transformers than the export toolchain reads; the conversion scripts in the toolkit swap in the base model's structurally identical config automatically.

Provenance

Qwen/Qwen3.6-27B, "AEON Ultimate Uncensored" tune by AEON-7, OpenVINO INT4 conversion (this repo).

Intended use and content notice

Uncensored general model, built and tested for roleplay and creative writing on local Intel hardware. The tune removes refusal behavior and outputs are unfiltered; you are responsible for lawful and appropriate use. Licensed under Apache 2.0, same as the upstream Qwen3.6 release.