The world's first reasoning-enhanced uncensored 397B model. Abliterated + LoRA fine-tuned on 12,842 high-quality reasoning samples distilled from Anthropic's Opus 4.6 outputs.

This is Stage 2 of the Qwen3.5-397B pipeline:

Stage 1 — Abliterated (refusals removed), no fine-tuning
Stage 2 (this repo) — Abliterated + LoRA reasoning fine-tune. Better chain-of-thought, deeper analysis, more structured problem-solving

397B total parameters, 17B active per token (Mixture-of-Experts). Trained for 3,046 steps across 8×H200 GPUs. Final loss: 0.363, accuracy: 90.2%.

What's Different From Stage 1

	Stage 1 (Abliterated Only)	Stage 2 (This Model)
Abliteration	✅ Custom pipeline	✅ Same pipeline
Fine-tuning	None	LoRA r=64, 134.7M trainable params
Training data	None	12,842 reasoning samples (Opus 4.6 distillation)
Reasoning quality	Base Qwen3.5	Enhanced chain-of-thought + structured analysis
Thinking mode	Default	Trained with `<think>` tags for explicit reasoning
Final loss	N/A	0.363
Final accuracy	N/A	90.2%

Training Details

LoRA Configuration:

Rank: 64, Alpha: 128
Target modules: self_attn.{q,k,v,o}_proj, shared_expert.{gate,up,down}_proj
Trainable parameters: 134.7M / 396.5B total (0.034%)
Gradient checkpointing: enabled

Training Hyperparameters:

Optimizer: AdamW (fused)
Learning rate: 1.5e-5 (cosine scheduler)
Effective batch size: 64
Sequence length: 4,096
Epochs: 2 (3,046 total steps)
Warmup: 3%
Precision: BF16

Dataset Composition (12,842 samples, deduplicated):

opus-10000x: 9,633 multi-turn conversations with deep reasoning
opus-3000x: 2,326 problem/thinking/solution samples with explicit chain-of-thought
reasoning-700x: 633 complex reasoning and analytical tasks
high-reasoning-250x: 250 elite-tier reasoning samples requiring multi-step deduction

All samples feature reasoning traces distilled from Anthropic's Claude Opus 4.6, including <think> tag formatting for explicit chain-of-thought.

Training Curve:

Step 0: Loss 0.83
Step 500: Loss ~0.52
Step 1000: Loss ~0.42
Step 2000: Loss ~0.39
Step 3046: Loss 0.363, Accuracy 90.2%

Quantizations

Quant	Size	BPW	RAM Required	Description	Use Case
BF16	739 GB (2 splits)	16.01	~750 GB	Full precision	Reference, maximum quality
Q8_0	393 GB	8.51	~400 GB	8-bit	Best quality with compression
Q6_K	304 GB	6.57	~310 GB	6-bit	High quality, good compression
Q4_K_M	225 GB	~4.85	~230 GB	4-bit mixed	Recommended for most users
Q3_K_M	177 GB	~3.83	~185 GB	3-bit mixed	Memory-constrained setups
Q2_K	135 GB	~2.92	~140 GB	2-bit	Extreme compression

Note: Q5_K_M is unavailable due to infrastructure loss during upload. Will be regenerated and uploaded in a future update.

Architecture

Type: Qwen3.5MoeForConditionalGeneration (hybrid GatedDeltaNet + MoE Transformer)
Total Parameters: 397B
Active Parameters: 17B per token
Hidden Size: 4,096
Layers: 60
Attention: 32 heads (GQA, 2 KV heads), head_dim 256
Experts: 512 routed + shared expert, 10 active per token
Hybrid Attention: GatedDeltaNet linear attention + self-attention every 4th layer
Context Length: 262,144 tokens
Vocab Size: 248,320
Multimodal: Native vision encoder (text + image + video)
Languages: 201+ (en, zh, ja, ko, fr, de, es, pt, ru, ar, th, vi, id, ...)
License: Apache 2.0

Usage

llama.cpp

bash

# Recommended: Q4_K_M for balanced quality/memory
./llama-cli -m Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-Q4_K_M.gguf \
  -p "You are a helpful uncensored assistant with strong reasoning abilities." \
  -n 2048 --temp 0.7 --top-p 0.9

# Server mode with large context
./llama-server -m Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-Q4_K_M.gguf \
  --port 8080 --host 0.0.0.0 -c 131072

LM Studio

Download the GGUF file and load it in LM Studio. The model supports <think> reasoning tags — enable thinking mode for best results on complex tasks.

Open WebUI / SillyTavern

Point your backend to a llama.cpp server. Full OpenAI-compatible API at /v1/chat/completions.

Pipeline

Qwen3.5-397B-A17B (base)
    ↓ Custom abliteration (strength 20.0, attn.o_proj + shared_expert.down_proj)
    ↓ LoRA fine-tuning (12,842 Opus 4.6 reasoning samples, 3,046 steps)
    ↓ LoRA merge into base weights
    ↓ BF16 GGUF conversion (llama.cpp)
    ↓ Quantization cascade (Q8_0 → Q2_K)

All processing done in BF16 on 8×H200 SXM5 GPUs (1.1TB VRAM total). Abliteration and quantization applied in correct order: full-precision abliteration → training → merge → THEN quantize.

Known Limitations

Q5_K_M missing: Lost during infrastructure migration. Will be regenerated.
Packed expert abliteration: The 512 routed experts use packed tensor format and were not individually abliterated. Some edge-case refusals may persist.
Vision: Multimodal vision encoder is preserved but untested post-training. Text generation is the primary target.
Thinking mode: The model generates <think> tags for reasoning. Strip them in post-processing if unwanted.

Model Provenance

Base model: Qwen/Qwen3.5-397B-A17B (Apache 2.0)
Stage 1: timteh673/Qwen3.5-397B-A17B-Uncensored-GGUF
Training data: Custom reasoning dataset distilled from Anthropic Opus 4.6 outputs
Quantization: llama.cpp
Hardware: 8×NVIDIA H200 SXM5, 1.1TB VRAM

Disclaimer

⚠️ This model has had safety alignment significantly reduced and has been fine-tuned for enhanced reasoning. It may generate content that is harmful, offensive, or inappropriate. Users are solely responsible for ensuring their use complies with applicable laws and ethical standards. This release is intended for research, testing, and controlled environments.

☕ Support This Work

Every donation helps fund more open-weight model releases. ⚡ Forged on 8×NVIDIA H200 SXM5 | 1.1TB VRAM

💎 Crypto Donations

Currency	Address
BTC	`bc1p4q7vpwucvww2y3x4nhps4y4vekye8uwm9re5a0kx8l6u5nky5ucszm2qhh`
ETH	`0xe5Aa16E53b141D42458ABeEDb00a157c3Fea2108`
SOL	`9CXwjG1mm9uLkxRevdMQiF61cr6TNHSiWtFRHmUEgzkG`

VECTORVV1/Qwen3.5-397B-A17B-Opus-4.6-Reasoning

Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF