ModelVerifiedExternal

Qwen3.6 27B Claude Opus Reasoning Distill v2 Heretic GGUF

Sourcehuggingface.co/fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF/tree/4c15c28a53c833ef2fd43a248c940b7178b0dae1

KindOtherBase modeldarkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-hereticVersionRevision 4c15c28Publisher@fzcfweasdferttggCgrade

Model source

Kind: Other
File size: 4.35–50.1 GB
Base model: darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic
Version: vRevision 4c15c28
Updated: Oct 4, 2026
Publisher: @fzcfweasdferttgg
Downloads: 2K
Parameters: 27B
Tasks: Text generation
Source: Hugging Face

Source description

Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic — GGUF

GGUF quantizations of darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

Model Overview

Property	Value
Base Model	Qwen/Qwen3.6-27B
Architecture	Qwen3.5ForConditionalGeneration
Parameters	27B (dense)
Context Length	262,144 tokens (256K)
License	Apache-2.0

Training Pipeline

Step 1: Claude Opus Reasoning Distillation

Fine-tuned on Claude Opus reasoning datasets using Unsloth + HuggingFace TRL (2x training speedup):

Step 2: Abliteration (Uncensoring)

Applied using Heretic v1.3.0. Reproducible via reproduce/ directory in the original repo.

Abliteration Parameters:

Parameter	Value
`direction_index`	41.77
`attn.o_proj.max_weight`	1.22
`attn.o_proj.max_weight_position`	51.32
`attn.o_proj.min_weight`	1.21
`attn.o_proj.min_weight_distance`	32.79
`mlp.down_proj.max_weight`	1.44
`mlp.down_proj.max_weight_position`	42.02
`mlp.down_proj.min_weight`	0.13
`mlp.down_proj.min_weight_distance`	37.15

Quality Metrics

KL Divergence & Refusal Rate

Metric	Value
KL Divergence (vs base)	0.0774
Refusals	8/100 (down from 98/100)

Benchmarks (mxfp8 precision)

Benchmark	Base Qwen3.6-27B	This Model	Delta
ARC	0.647	0.665	+1.8%
ARC-E	0.803	0.831	+2.8%
BoolQ	0.910	0.910	0.0%
HellaSwag	0.773	0.790	+1.7%
OpenBookQA	0.450	0.456	+0.6%
PIQA	0.806	0.813	+0.7%
WinoGrande	0.742	0.772	+3.0%

Available Quantizations

File	Size	BPW
`*-f16.gguf`	~50 GB	16.0
`*-Q1_0.gguf`	~4 GB	1.1
`*-Q2_K.gguf`	~10 GB	2.5
`*-Q3_K_S.gguf`	~11 GB	3.0
`*-Q3_K_M.gguf`	~12 GB	3.5
`*-Q3_K_L.gguf`	~13 GB	3.8
`*-Q4_0.gguf`	~14 GB	4.0
`*-Q4_1.gguf`	~16 GB	4.8
`*-Q4_K_S.gguf`	~15 GB	4.0
`*-Q4_K_M.gguf`	~15 GB	4.5
`*-Q5_0.gguf`	~17 GB	5.0
`*-Q5_1.gguf`	~19 GB	5.7
`*-Q5_K_S.gguf`	~17 GB	5.0
`*-Q5_K_M.gguf`	~18 GB	5.5
`*-Q6_K.gguf`	~21 GB	6.0
`*-Q8_0.gguf`	~27 GB	8.0

Quantization Details

f16: Full float16 precision, lossless conversion from safetensors
Q1_0: Extreme compression, very low quality
Q2_K: Smallest practical size, lower quality
Q3_K_S / Q3_K_M / Q3_K_L: Q3 variants with increasing quality
Q4_0 / Q4_1: Legacy formats, compatible with older tools
Q4_K_S / Q4_K_M: K-quant mixtures with balanced quality/size
Q5_0 / Q5_1: Legacy formats, compatible with older tools
Q5_K_S / Q5_K_M: K-quant mixtures with high quality
Q6_K: Highest quality K-quant
Q8_0: Near-lossless, 8-bit integer quantization

System Requirements

Quant	VRAM
f16	~50 GB
Q1_0	~4 GB
Q2_K	~10 GB
Q3_K_S	~11 GB
Q3_K_M	~12 GB
Q3_K_L	~13 GB
Q4_0	~14 GB
Q4_1	~16 GB
Q4_K_S	~15 GB
Q4_K_M	~15 GB
Q5_0	~17 GB
Q5_1	~19 GB
Q5_K_S	~17 GB
Q5_K_M	~18 GB
Q6_K	~21 GB
Q8_0	~27 GB

Recommended Settings

Temperature: 0.7
Top-p: 0.9
Top-k: 40
Repeat penalty: 1.1

Links

Original model: darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic
Base model: Qwen/Qwen3.6-27B
Distillation source: TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
Heretic tool: Heretic v1.3.0

Sources

1 source

Hugging FacePrimaryVersion 4c15c28a53c833ef2fd43a248c940b7178b0dae1

huggingface.co/fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF/tree/4c15c28a53c833ef2fd43a248c940b7178b0dae1

Verified Oct 4

Model artifacts

16 artifacts

qwen3.6-27b-opus-hereticv2-f16.gguf

gguf · 50.1 GB · SHA-256 d269420b0a47…75e1 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q1_0.gguf

gguf · 4.35 GB · SHA-256 9b3847c7850a…3fc9 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q2_K.gguf

gguf · 9.98 GB · SHA-256 cef640879d54…b78d · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q3_K_L.gguf

gguf · 13.4 GB · SHA-256 0be9cd0e5940…f79e · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q3_K_M.gguf

gguf · 12.4 GB · SHA-256 6949d5080e62…97dc · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q3_K_S.gguf

gguf · 11.2 GB · SHA-256 13f72fa75255…b22b · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q4_0.gguf

gguf · 14.4 GB · SHA-256 d953ad6fd4e3…fdd7 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q4_1.gguf

gguf · 15.9 GB · SHA-256 95c50b12c1ec…7dd5 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q4_K_M.gguf

gguf · 15.4 GB · SHA-256 cc72da22bd96…9878 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q4_K_S.gguf

gguf · 14.5 GB · SHA-256 7c78228aa331…7a88 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q5_0.gguf

gguf · 17.4 GB · SHA-256 7b6312569e47…25e9 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q5_1.gguf

gguf · 18.9 GB · SHA-256 c331280cd4b6…e0d6 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q5_K_M.gguf

gguf · 17.9 GB · SHA-256 3ded64a6812f…c595 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q5_K_S.gguf

gguf · 17.4 GB · SHA-256 e6348f2f623e…b904 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q6_K.gguf

gguf · 20.6 GB · SHA-256 85a9bf5299a0…9e64 · Hugging Face

Download

qwen3.6-27b-opus-hereticv2-Q8_0.gguf

gguf · 26.6 GB · SHA-256 262f2174d85f…4c58 · Hugging Face

Download

Source excerpts

3 excerpts

ReadmeJul 13huggingface.co/fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF

--- tags: - text-generation-inference - transformers - qwen3.6 - heretic - uncensored - decensored - abliterated - reproducible - llama-cpp - gguf-my-repo license: apache-2.0 base_model: - darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic datasets: - TeichAI/claude-4.5-opus-high-reasoning-250x - TeichAI/Claude-Opus-4.6-Reasoning-887x --- # Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic — GGUF GGUF quantizations of [darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic](https://huggingface.co/darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic) ## Model Overview | Property | Value | |---|---| | **Base Model** | Qwen/Qwen3.6-27B | | **Architecture** | Qwen3.5ForConditionalGeneration | | **Parameters** | 27B (dense) | | **Context Length** | 262,144 tokens (256K) | | **License** | Apache-2.0 | ## Training Pipeline ### Step 1: Claude Opus Reasoning Distillation Fine-tuned on Claude Opus reasoning datasets using **Unsloth + HuggingFace TRL** (2x training speedup): - [`TeichAI/Claude-Opus-4.6-Reasoning-887x`](https://huggingface.co/datasets/TeichAI/Claude-Opus-4.6-Reasoning-887x) - [`TeichAI/claude-4.5-opus-high-reasoning-250x`](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) ### Step 2: Abliteration (Uncensoring) Applied using **Heretic v1.3.0**. Reproducible via `reproduce/` directory in the original repo. **Abliteration Parameters:** | Parameter | Value | |---|---| | `direction_index` | 41.77 | | `attn.o_proj.max_weight` | 1.22 | | `attn.o_proj.max_weight_position` | 51.32 | | `attn.o_proj.min_weight` | 1.21 | | `attn.o_proj.min_weight_distance` | 32.79 | | `mlp.down_proj.max_weight` | 1.44 | | `mlp.down_proj.max_weight_position` | 42.02 | | `mlp.down_proj.min_weight` | 0.13 | | `mlp.down_proj.min_weight_distance` | 37.15 | ## Quality Metrics ### KL Divergence & Refusal Rate | Metric | Value | |---|---| | **KL Divergence** (vs base) | 0.0774 | | **Refusals** | 8/100 (down from 98/100) | ### Benchmarks (mxfp8 precision) | Benchmark | Base Qwen3.6-27B | This Model | Delta | |---|---|---|---| | **ARC** | 0.647 | 0.665 | +1.8% | | **ARC-E** | 0.803 | 0.831 | +2.8% | | **BoolQ** | 0.910 | 0.910 | 0.0% | | **HellaSwag** | 0.773 | 0.790 | +1.7% | | **OpenBookQA** | 0.450 | 0.456 | +0.6% | | **PIQA** | 0.806 | 0.813 | +0.7% | | **WinoGrande** | 0.742 | 0.772 | +3.0% | ## Available Quan...

NoteOct 4huggingface.co/fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF

Source context: 1999 downloads · 0 likes · Library transformers · Repo fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF

NoteJul 18huggingface.co/fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF

Source context: 1142 downloads · 0 likes · Library transformers · Repo fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF