SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF overview
library name: transformers license: apache 2.0 license link: https://huggingface.co/Qwen/Qwen3.6 35B A3B/blob/main/LICENSE pipeline tag: image text to text tag…
Runs locally from ~857.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Balanced.gguf | GGUF | GGUF | 24.18 GB | Download |
| Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact.gguf | GGUF | GGUF | 15.85 GB | Download |
| Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Quality.gguf | GGUF | GGUF | 21.90 GB | Download |
| mmproj-Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-F16.gguf | GGUF | F16 | 857.6 MB | Download |
Model Details
| Model ID | SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF |
|---|---|
| Author | SC117 |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved |
| Last modified | 2026-06-26T05:39:32.000Z |
Model README
---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
tags:
- qwen3_5_moe
- qwen3_5
- heretic
- uncensored
- decensored
- abliterated
- mpoa
- mtp
- apex
- quantization
base_model:
- llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved
---
<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; margin-bottom: 24px;">
<div style="background: #f5f5f7; border-radius: 20px; padding: 36px 32px; margin-bottom: 20px; text-align: center; position: relative; overflow: hidden;">
<div style="position: absolute; top: -30px; right: -30px; width: 120px; height: 120px; background: #ffedd5; border-radius: 50%;"></div>
<div style="position: absolute; bottom: -20px; left: 40px; width: 80px; height: 80px; background: #fed7aa; border-radius: 50%;"></div>
<div style="position: absolute; top: 50%; left: -15px; width: 60px; height: 60px; background: #ffedd5; border-radius: 50%;"></div>
<div style="display: inline-flex; gap: 8px; margin-bottom: 16px; position: relative; z-index: 1;">
<span style="background: #007aff; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">APEX</span>
<span style="background: #af52de; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">MTP</span>
<span style="background: #ff3b30; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">Uncensored</span>
</div>
<h1 style="margin: 0 0 8px 0; font-size: 32px; font-weight: 700; color: #1d1d1f; letter-spacing: -0.5px; border: none; position: relative; z-index: 1;">Qwen3.6-35B-A3B</h1>
<p style="margin: 8px 0 0 0; font-size: 14px; position: relative; z-index: 1;"><span style="color: #86868b;">English</span> | <a href="https://huggingface.co/SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF/blob/main/README_zh.md" style="color: #007aff; text-decoration: none;">📖 中文文档</a></p>
<p style="margin: 0; font-size: 15px; color: #86868b;
</div>
</div>
<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; display: flex; flex-direction: column; gap: 20px; margin-bottom: 30px;">
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02); margin-bottom: 20px;">
<div style="background: linear-gradient(135deg, #10b981 0%, #059669 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🔄</span> Update (2026-06-26)</div>
<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">
<p style="margin: 0 0 8px 0;">Optimized quantization strategy with improved imatrix calibration. File sizes reduced while maintaining quality:</p>
<ul style="margin: 0; padding-left: 20px;">
<li>I-Compact: 16.61 GB → <b>15.85 GB</b> (-0.76 GB)</li>
<li>I-Balanced: 24.24 GB → <b>24.18 GB</b> (-0.06 GB)</li>
<li>I-Quality: 21.90 GB → <b>21.90 GB</b> (unchanged)</li>
</ul>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>💡</span> What is APEX?</div>
<div style="padding: 16px;">
<p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7;">These GGUF files are quantized using <a href="https://github.com/mudler/apex-quant" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">APEX</a>, a novel MoE-aware mixed-precision quantization technique that outperforms standard quantization methods while being significantly smaller.</p>
<p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7; font-weight: 700;">APEX beats Q8_0 perplexity at half the size — and even beats F16.</p>
<p style="margin: 0; font-size: 13px; color: #334155; line-height: 1.7;">APEX classifies every tensor by its role — routed expert, shared expert, or attention — and applies a layer-wise precision gradient, giving the most sensitive edge layers higher precision and compressing the redundant middle layers more aggressively.</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📦</span> APEX Quantization Tiers</div>
<div style="padding: 16px;">
<table style="width: 100%; border-collapse: collapse; font-size: 13px;"><thead><tr style="background: rgba(255,107,53,0.05);"><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 35%;">File</th><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 15%;">Size</th><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 15%;">Profile</th><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 35%;">Best For</th></tr></thead><tbody>
<tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;"><code>*-APEX-I-Quality.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">21.90 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">I-Quality</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">Highest quality, best accuracy</td></tr>
<tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;"><code>*-APEX-I-Balanced.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">24.18 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">I-Balanced</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">Best all-rounder, recommended</td></tr>
<tr><td style="padding: 8px 10px; color: #334155;"><code>*-APEX-I-Compact.gguf</code></td><td style="padding: 8px 10px; color: #334155;">15.85 GB</td><td style="padding: 8px 10px; color: #334155;">I-Compact</td><td style="padding: 8px 10px; color: #334155;">Best quality/size ratio</td></tr>
</tbody></table>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📊</span> Why APEX?</div>
<div style="padding: 16px;">
<table style="width: 100%; border-collapse: collapse; font-size: 13px;"><thead><tr style="background: rgba(255,107,53,0.05);"><th style="padding: 7px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 22%;">Method</th><th style="padding: 7px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 15%;">Size</th><th style="padding: 7px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 20%;">Perplexity</th><th style="padding: 7px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 20%;">HellaSwag</th><th style="padding: 7px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 15%;">Speed</th></tr></thead><tbody>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">F16</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">64.6 GB</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">6.537</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">82.5%</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">30.4 t/s</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">Q8_0</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">34.4 GB</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">6.533</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">83.0%</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">52.5 t/s</td></tr>
<tr style="background: rgba(255,107,53,0.04);"><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #c2410c; background: white;">APEX I-Quality</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">21.3 GB</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">6.552</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">83.5%</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">63.1 t/s</td></tr>
<tr style="background: rgba(255,107,53,0.04);"><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #c2410c; background: white;">APEX I-Balanced</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">23.6 GB</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">6.548</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">83.0%</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">61.4 t/s</td></tr>
<tr style="background: rgba(255,107,53,0.04);"><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #c2410c; background: white;">APEX I-Compact</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">16.1 GB</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">6.669</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">81.8%</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">69.8 t/s</td></tr>
<tr style="background: rgba(255,107,53,0.04);"><td style="padding: 6px 10px; font-weight: bold; color: #c2410c; background: white;">APEX Mini</td><td style="padding: 6px 10px; font-weight: bold; color: #334155;">12.2 GB</td><td style="padding: 6px 10px; font-weight: bold; color: #334155;">7.088</td><td style="padding: 6px 10px; font-weight: bold; color: #334155;">81.0%</td><td style="padding: 6px 10px; font-weight: bold; color: #334155;">74.4 t/s</td></tr>
</tbody></table>
<p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; font-style: italic;">Benchmarks on Qwen3.5-35B-A3B, NVIDIA DGX Spark (GB10, 122 GB VRAM).</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📐</span> I-Variant: Diverse Imatrix Calibration</div>
<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">
<p style="margin: 0;">I-variants use a diverse calibration dataset spanning chat, code, reasoning, and tool-calling — no Wikipedia. This produces higher accuracy on real-world benchmarks, lower KL divergence, and tiny perplexity increase on wikitext.</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🔓</span> Original Model</div>
<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">
<p style="margin: 0 0 12px 0;"><b>Base</b>: <a href="https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved</a></p>
<p style="margin: 0 0 12px 0;">Decensored version of <a href="https://huggingface.co/Qwen/Qwen3.6-35B-A3B" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">Qwen/Qwen3.6-35B-A3B</a>, made using <a href="https://github.com/p-e-w/heretic" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">Heretic</a> v1.3.0 + <a href="https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">MPOA</a>.</p>
<p style="margin: 0;"><b>88% fewer refusals</b> (10/100 Uncensored vs 83/100 Original) while preserving model quality (0.0015 KL divergence).</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>⚡</span> MTP Speculative Decoding</div>
<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">
<p style="margin: 0 0 12px 0;">All 20 MTP layers preserved. Use <code>--spec-type draft-mtp --spec-draft-n-max 2</code> for <b>20-50% speed boost</b>.</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🧠</span> Model Details</div>
<div style="padding: 16px;">
<table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Architecture</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Qwen3.5 MoE (Mixture of Experts)</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Parameters</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">35B total, 3B active per token</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Experts</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">256 routed experts, 8 active per token</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Layers</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">40 transformer layers + 1 MTP layer</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Context</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">262,144 tokens</td></tr>
<tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">Decensoring</td><td style="padding: 6px 10px; color: #4b5563; background: white;">Heretic v1.3.0 + MPOA (88% fewer refusals, 0.0015 KL)</td></tr>
</tbody></table>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🚀</span> Usage</div>
<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">
<p style="margin: 0 0 8px 0; font-weight: bold; color: #1e293b;">llama.cpp</p>
<p style="margin: 0; font-family: monospace; background: #f8fafc; padding: 10px 14px; border-radius: 6px; border: 1px solid #e2e8f0; font-size: 12px; color: #1e293b; white-space: pre-wrap;">hf download SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF --include "*.gguf" --local-dir ./models
./llama-server -m ./models/...APEX-I-Compact.gguf -ngl 99 -ncmoe 16 -c 131072 --spec-type draft-mtp --spec-draft-n-max 2</p>
<p style="margin: 12px 0 8px 0; font-weight: bold; color: #1e293b;">Ollama</p>
<p style="margin: 0; font-family: monospace; background: #f8fafc; padding: 10px 14px; border-radius: 6px; border: 1px solid #e2e8f0; font-size: 12px; color: #1e293b; white-space: pre-wrap;">echo 'FROM ./...APEX-I-Compact.gguf' > Modelfile
ollama create my-model -f Modelfile && ollama run my-model</p>
</div>
</div>
<div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);">
<div style="background: linear-gradient(135deg, #ff6b35 0%, #f7931e 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🎛️</span> Recommended Settings</div>
<div style="padding: 16px;">
<table style="width: 100%; border-collapse: collapse; font-size: 13px;"><thead><tr style="background: rgba(255,107,53,0.05);"><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 30%;">Mode</th><th style="padding: 8px 10px; border-bottom: 2px solid #ff6b35; text-align: left; color: #c2410c; font-weight: bold; width: 70%;">Parameters</th></tr></thead><tbody>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Thinking (general)</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white; font-family: monospace;">temp=1.0, top_p=0.95, top_k=20, pres_penalty=1.5</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Thinking (coding)</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white; font-family: monospace;">temp=0.6, top_p=0.95, top_k=20</td></tr>
<tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Instruct (general)</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white; font-family: monospace;">temp=0.7, top_p=0.8, top_k=20, pres_penalty=1.5</td></tr>
<tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">Instruct (reasoning)</td><td style="padding: 6px 10px; color: #4b5563; font-family: monospace; background: white;">temp=1.0, top_p=1.0, top_k=40, pres_penalty=2.0</td></tr>
</tbody></table>
</div>
</div>
</div>
Links
- APEX Quantization: https://github.com/mudler/apex-quant
- Original Model: https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved
- Heretic: https://github.com/p-e-w/heretic
- Qwen3.6-35B-A3B: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
Citation
@misc{qwen36_35b_a3b,
title = {{Qwen3.6-35B-A3B}: Agentic Coding Power, Now Open to All},
url = {https://qwen.ai/blog?id=qwen3.6-35b-a3b},
author = {{Qwen Team}},
month = {April},
year = {2026}
}Run SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models