---
title: QwenPaw-Flash-9B-heretic-1M-GGUF
canonical_url: "https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF"
md_url: "https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF.md"
repository: satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF
last_updated: 2026-07-06
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - Qwen/Qwen3.5-9B
  - agentscope-ai/QwenPaw-Flash-9B
  - SC117/QwenPaw-Flash-9B-heretic-MTP-GGUF
base_model_relation: quantized
library_name:
  - gguf
language:
  - en
  - zh
downloads: 182
stars: 0
tags:
  - gguf
  - long-context
  - yarn
  - qwen3.5
  - heretic
  - uncensored
  - mtp
  - speculative-decoding
  - vision
  - agent
  - tool-call
  - llama.cpp
  - ollama
---

# QwenPaw-Flash-9B-heretic-1M-GGUF

> QwenPaw-Flash-9B-heretic-1M-GGUF - An open-source model by satgeze on ModelScope. 1M CONTEXT MTP VISION UNCENSORED QwenPaw-Flash-9B-heretic-1M Agent-optimized 9B, uncensored, with a needle-verified million-token context

satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF is a text-generation model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3.5-9B、agentscope-ai/QwenPaw-Flash-9B、SC117/QwenPaw-Flash-9B-heretic-MTP-GGUF.

- **Repository**: satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF
- **License**: apache-2.0
- **Tasks**: text-generation
- **Base model**: Qwen/Qwen3.5-9B, agentscope-ai/QwenPaw-Flash-9B, SC117/QwenPaw-Flash-9B-heretic-MTP-GGUF
- **Tags**: gguf, long-context, yarn, qwen3.5, heretic, uncensored, mtp, speculative-decoding, vision, agent, tool-call, llama.cpp, ollama
- **Downloads**: 182
- **Stars**: 0
- **Last updated**: 2026-07-06

Source: https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF

---

<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; margin-bottom: 30px;">
<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: #34c759; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">1M CONTEXT</span><span style="background: #007aff; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">MTP</span><span style="background: #af52de; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">VISION</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;">QwenPaw-Flash-9B-heretic-1M</h1>
  <p style="margin: 8px 0 0 0; font-size: 14px; color: #86868b; position: relative; z-index: 1;">Agent-optimized 9B, uncensored, with a needle-verified million-token context</p>
</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);">
    <div style="padding: 16px;">
      <p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7;"><a href="https://huggingface.co/SC117/QwenPaw-Flash-9B-heretic-MTP-GGUF" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">SC117's heretic build</a> of <a href="https://huggingface.co/agentscope-ai/QwenPaw-Flash-9B" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">QwenPaw-Flash-9B</a> (agent-trajectory finetune of Qwen3.5-9B) with YaRN rope scaling <b>baked into the GGUF metadata for a 1,048,576-token context window</b>, 4x the native 262,144. Weights are bit-identical to SC117's release, which already carries the official Qwen3.5-9B MTP layer injected back after the QwenPaw fine-tuning stripped it.</p>
      <p style="margin: 0; font-size: 13px; color: #334155; line-height: 1.7;"><i>Uncensored (Heretic v1.3.0) · MTP baked in · Vision tower included · 1M needle-verified</i></p>
    </div>
  </div>
</div>

## Verified on these exact files

| Capability | Result |
|---|---|
| 1M context | 10 needles per rung, depths 5 to 95 percent, temp 0, Q8_0 + f16 KV: **10/10 at every rung from 64K through 524K** on an RTX 5090; 786K and 1M rungs running on a 128 GB M3 Max, card updates when they land |
| MTP speculative decoding | 217.9 to 273.2 tok/s (**+25 percent**), draft acceptance 0.702, output identical by construction |
| Vision | mmproj tower reads image text and identifies objects correctly |
| Coherence | Q8_0 and Q4_K_M both pass the repetition-collapse gate |

<img src="niah_heatmap.png" width="640"/>

<img src="mtp_speedup.png" width="480"/>

Raw per-needle records including every run: `results.jsonl`.

## Files

| File | Size | Pick it when |
|---|---|---|
| `qwenpaw-9b-1M-MTP-Q8_0.gguf` | 9.8 GB | Max quality. On a 128 GB Mac this runs the full 1M with f16 KV (~43 GB total) |
| `qwenpaw-9b-1M-MTP-Q4_K_M.gguf` | 5.8 GB | 32 GB GPUs. Full 1M fits with q8_0 KV (budget config); ~524K at f16 KV |
| `mmproj-qwenpaw-9b.gguf` | 0.9 GB | Vision, attach with `--mmproj` |

No other quants on purpose: the 9B is small enough that Q8_0 is the sensible default and Q4_K_M covers the budget case.

## Every file, every mirror

Nothing was discontinued: every quant is one click away. Hugging Face carries the curated picks, ModelScope always carries everything, and Ollama serves ready-to-run tags.

On Ollama every tag ships with the vision tower bundled and the 1M rope metadata baked in.

| File | Size | Hugging Face | ModelScope | Ollama |
|---|---|---|---|---|
| `mmproj-qwenpaw-9b.gguf` | 922 MB | [download](https://huggingface.co/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/main/mmproj-qwenpaw-9b.gguf) | [download](https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/master/mmproj-qwenpaw-9b.gguf) | bundled in every tag |
| `qwenpaw-9b-1M-MTP-Q4_K_M.gguf` | 5.8 GB | [download](https://huggingface.co/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/main/qwenpaw-9b-1M-MTP-Q4_K_M.gguf) | [download](https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/master/qwenpaw-9b-1M-MTP-Q4_K_M.gguf) | [`ollama run satgeze/qwenpaw-9b-heretic-1m:q4_k_m`](https://ollama.com/satgeze/qwenpaw-9b-heretic-1m) |
| `qwenpaw-9b-1M-MTP-Q8_0.gguf` | 9.8 GB | [download](https://huggingface.co/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/main/qwenpaw-9b-1M-MTP-Q8_0.gguf) | [download](https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF/resolve/master/qwenpaw-9b-1M-MTP-Q8_0.gguf) | [`ollama run satgeze/qwenpaw-9b-heretic-1m`](https://ollama.com/satgeze/qwenpaw-9b-heretic-1m) |

## Run it

```bash
llama-server -m qwenpaw-9b-1M-MTP-Q8_0.gguf \
  -c 1048576 -np 1 --jinja \
  --spec-type draft-mtp --spec-draft-n-max 3 \
  --mmproj mmproj-qwenpaw-9b.gguf
```

Ollama (1M and vision work; no speculative decoding in Ollama yet):

```
FROM ./qwenpaw-9b-1M-MTP-Q8_0.gguf
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER num_ctx 262144
```

## How this was built

YaRN rope-scaling metadata (factor 4.0 over native 262,144) written into the GGUF header with gguf-py. No weight changes, no fine-tuning by us. Certification: multi-needle harness against llama-server, f16 KV only for cert runs. Method and tooling: [github.com/satindergrewal/aviary-1m](https://github.com/satindergrewal/aviary-1m).

Note on upstream speed claims: SC117 reports up to 4.1x on time-scored agent benchmarks. Our controlled A/B on identical prompts measures +25 percent decode; speculative decoding cannot change model outputs at temperature 0, so treat benchmark-score deltas from MTP as timing artifacts.

## Credits

Base: [Qwen](https://huggingface.co/Qwen/Qwen3.5-9B) (Apache-2.0), including the MTP layer and vision tower. Agent fine-tune: [agentscope-ai](https://huggingface.co/agentscope-ai/QwenPaw-Flash-9B). Heretic abliteration and MTP re-injection: [SC117](https://huggingface.co/SC117). 1M YaRN extension and certification: [SatGeze](https://huggingface.co/satgeze).

Mirrors: [Hugging Face](https://huggingface.co/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF) | [ModelScope](https://www.modelscope.ai/models/satgeze/QwenPaw-Flash-9B-heretic-1M-GGUF). Sister repos: [Uncensored 1M collection](https://huggingface.co/collections/satgeze/uncensored-1m-context-gemma-4-qwen36-6a4b33493b132e3da13b2c29)