---
license: apache-2.0
base_model: Qwen/Qwen3.6-27B
tags:
  - qwen3
  - qwen3.6
  - aeon-rys
  - abliterated
  - uncensored
  - agentic
  - coding-agent
  - gguf
  - ik-llama
  - hybrid-attention
  - mamba
  - gated-deltanet
library_name: gguf
pipeline_tag: text-generation
language:
  - en
  - zh
---

# Qwen3.6-27B-AEON-RYS-Agentic-Coder-PatchCode (GGUF)

An agentic-coder behaviour distill on the **Qwen3.6-27B-AEON-RYS** base (itself an Apache-2.0 abliteration of `Qwen/Qwen3.6-27B`). Tuned for action-first, narrate→act→verify coding-agent discipline: minimal preamble, claims backed by an actual run, systematic diagnose→fix loops, and stable multi-turn tool use. Distilled from execution traces of a high-discipline coding agent blended with a robust narrate-act-verify coding dataset.

**Recommended file: `…IQ4_NL.gguf` (16.6 GB)** — behaviourally indistinguishable from BF16 across a 5-seed, same-condition bake-off (build / long-context / discipline / autonomous-loop all tied within noise), at ~⅓ the size.

---

## ⚠️ READ FIRST — special loader required (qwen3_5 triple-hybrid arch)

This model uses Qwen3.6's **triple-hybrid** architecture (`model_type: qwen3_5`: full self-attention every 4th layer + linear-attention / GatedDeltaNet / SSM + MLP). **Mainline `llama.cpp` and `vLLM` will NOT load it** (`missing tensor blk.N.ssm_conv1d.weight`).

Use a loader with `qwen35` arch support. Verified working options:

1. **[ikawrakow/ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp)** — `qwen35` (`LLM_ARCH_QWEN35`) is upstream. Build from `main` and it loads + serves this model on NVIDIA 50-series (and others).
2. **[noonr48/qwen36-aeon-ik-llama](https://github.com/noonr48/qwen36-aeon-ik-llama)** — a documented fork (build + serve guides, quant recipes for this model line). `main` was verified to load + serve `…IQ4_NL.gguf` on 2× RTX 5060 Ti.

Build (CUDA):
```bash
cmake -B build -DGGML_CUDA=ON \
  -DCMAKE_CUDA_ARCHITECTURES="86;120" \
  -DCOMPRESSION_MODE=speed   # ik_llama speed build
cmake --build build --config Release -j
```

An optional MTP speculative-decoding **speed** patch is bundled as `qwen36-mtp-rys_delta.patch` (it is **not** required to load/serve — only for the decode speed-up; without it the server uses normal autoregressive decode).

---

## Serve (ik_llama / ik-llama.cpp)

```bash
llama-server \
  -m Qwen3.6-27B-AEON-RYS-Agentic-Coder-PatchCode.IQ4_NL.gguf \
  -a patchcode --host 0.0.0.0 --port 8000 \
  -ngl 99 -c 163840 -ctk f16 -ctv f16 -b 512 -ub 128 \
  --jinja --reasoning-format deepseek --flash-attn on
```

- **`<think>` is emitted as a separate `reasoning_content` field** (not in `content`). Use `--reasoning-format deepseek` (or fold `reasoning_content` back into `<think>…</think>` in your harness) so tool-action parsing sees the action, not the chain-of-thought.
- IQ4_NL (16.6 GB weights) + f16 KV at 160k ctx ≈ ~45–55 GB VRAM total → fits comfortably on a single 80 GB card or a small multi-card pool.

---

## Files

| file | size | notes |
|---|---|---|
| `Qwen3.6-27B-AEON-RYS-Agentic-Coder-PatchCode.IQ4_NL.gguf` | 16.6 GB | **Recommended.** Plain IQ4_NL, reasoning/coding imatrix. Ship pick. |
| `Qwen3.6-27B-AEON-RYS-Agentic-Coder-PatchCode.BF16.gguf` | 57.6 GB | Full-precision source / control ceiling. |
| `qwen36-mtp-rys_delta.patch` | 57 KB | Optional ik_llama MTP speed patch (loader not required for use). |

---

## Quant bake-off (why IQ4_NL ships over BF16 / Q8 / mixed recipes)

Full 5-phase bake-off using a hardened SignalLatch-style methodology (the discriminator is a 160k-token real-world multi-file build, scored multi-seed — single-shot coding gates saturate and were rejected):

| candidate | build (KritaLite) | long-context | discipline | autonomy-loop | size |
|---|---|---|---|---|---|
| **IQ4_NL (reasoning imatrix)** | 0.920 (±0.067) | 0.975 | 0.842 (±0.333) | 100% / 0% halluc | **16 G** |
| BF16 (control) | 0.867 | 0.942 | 0.931 | — | 58 G |
| Q8_0 | 0.867 | 0.969 | 0.742 | 100% | 29 G |
| mixed-recipe (promoted attn) | 0.907–0.933 | 0.935 | 0.69–0.90 | 100% | 20–24 G |

- **IQ4_NL ties BF16 within noise** on build / long-context / discipline / autonomous-loop convergence (8 held-out agentic tasks × 5 seeds: 100% convergence, 0% hallucinated-success, 0% stall for every quant). Near-lossless Q8 and promoted-attention mixed recipes bought **no measurable edge** and cost 2–6× the size.
- **Key methodology lesson:** on this suite, KritaLite build has ±0.067–0.13 run-to-run variance and discipline ±0.3. A 3-seed single-condition run shipped a *false* winner (a mixed recipe scored 0.933 once, never reproduced). Only 5+ seed same-condition head-to-heads + non-noise axes (size, recipe safety) reliably tiebreak. IQ4_NL wins on size + the plain-quant recipe (no promotion risk).

---

## Lineage

```
Qwen/Qwen3.6-27B                      (Apache-2.0)
  └─ AEON-RYS abliteration            (uncensored; safety rails surgically removed)
       └─ + prior behaviour LoRA @ light strength   →  ckpt386_s010
            └─ + Agentic-Coder joint LoRA @ λ=0.5   →  this model (merged_lam0.5)
```

`base_model` lineage: `Qwen/Qwen3.6-27B` → AEON-RYS → `ckpt386_s010` (AEON-RYS + a light prior behaviour LoRA) → this model (joint agentic-coder LoRA, checkpoint-3661, merged at λ=0.5).

---

## License

Apache-2.0, inherited from `Qwen/Qwen3.6-27B` (and the AEON-RYS abliteration). The Qwen3.6 base license permits derivative redistribution; attribute the base model and the AEON-RYS abliteration.

> Uncensored / abliterated: this derivative has had refusal/safety steering removed at the base. Use responsibly and in accordance with your local laws and platform policies.