---
license: apache-2.0
base_model:
  - Qwen/Qwen3.5-9B
pipeline_tag: text-generation
library_name: vllm
tags:
  - blackfrost
  - the-void
  - pinqwen
  - 1m-context
  - uncensored
  - reasoning
  - long-context
  - coding
  - nvfp4
  - blackwell
---

![PINQWEN-3.5-9B-1M](./hero.jpg)

<p align="center">
  <img src="https://img.shields.io/badge/context-1%2C000%2C000_tokens-8A2BE2?style=for-the-badge" alt="1M context">
  <img src="https://img.shields.io/badge/alignment-UNCENSORED-c0143c?style=for-the-badge" alt="Uncensored">
  <img src="https://img.shields.io/badge/quant-NVFP4-9A2BE2?style=for-the-badge" alt="NVFP4">
  <img src="https://img.shields.io/badge/GPU-Blackwell-76b900?style=for-the-badge" alt="Blackwell">
  <img src="https://img.shields.io/badge/license-Apache_2.0-2ea44f?style=for-the-badge" alt="Apache 2.0">
</p>

# PINQWEN‑3.5‑9B‑1M — NVFP4

> ### 🪟 **A 9B that reads a *million* tokens, thinks before it speaks, and never refuses — now in 4‑bit for Blackwell.**

**PINQWEN‑3.5‑9B‑1M** is Blackfrost AI's compact powerhouse — a reasoning model distilled through **The Void**, our multi‑teacher reasoning‑distillation method, on the **Qwen 3.5 9B** architecture. It reasons first and answers second (`<think>` → answer), across a **full one‑million‑token context window**. This is the **NVFP4** build: 4‑bit weights tuned for blazing‑fast serving on NVIDIA Blackwell.

<!-- 👉 hero image goes here -->

---

## 🚀 Why PINQWEN‑3.5‑9B‑1M?

| | |
|---|---|
| 🪟 **1,000,000‑token context** | Whole codebases and document sets in a single prompt — YaRN‑extended on a hybrid backbone built for fast long context. |
| 🔓 **Uncensored** | Answers directly, no reflexive refusals. You're in control. |
| 🧠 **Reasons in the open** | Native `<think>…</think>` chain‑of‑thought from a panel of frontier teachers. |
| ⚡ **Blackwell‑native** | Weight‑only NVFP4 (group‑size 16) — a fraction of BF16's footprint, tuned for RTX PRO 6000 / B‑series. |

## 📦 This repository — NVFP4

A **weight‑only NVFP4** (4‑bit, group‑size 16) build of the text backbone for **NVIDIA Blackwell**, with attention and output layers kept at higher precision. This is the **text serving** variant (vision not included) — use the BF16 or GGUF repo for multimodal. **Full 1M context.**

## ⚡ Quickstart (vLLM on Blackwell)

```bash
vllm serve Blackfrost-AI/PINQWEN-3.5-9B-1M-NVFP4 \
  --quantization modelopt_fp4 --kv-cache-dtype fp8 \
  --reasoning-parser qwen3 --max-model-len 1048576
```

## 🎛 Formats — every one is 1M context

| Format | Repository | Best for |
|---|---|---|
| **BF16** | [`PINQWEN-3.5-9B-1M-BF16`](https://huggingface.co/Blackfrost-AI/PINQWEN-3.5-9B-1M-BF16) | Reference precision, fine‑tuning, vision |
| **NVFP4** | [`PINQWEN-3.5-9B-1M-NVFP4`](https://huggingface.co/Blackfrost-AI/PINQWEN-3.5-9B-1M-NVFP4) | Fast serving on NVIDIA Blackwell |
| **GGUF** | [`PINQWEN-3.5-9B-1M-GGUF`](https://huggingface.co/Blackfrost-AI/PINQWEN-3.5-9B-1M-GGUF) | llama.cpp / local — full quant ladder + MTP |

## 📄 License

**Apache‑2.0.** Base architecture: Qwen 3.5 9B. As an uncensored model, use responsibly.

---

<p align="center"><em>PINQWEN‑3.5‑9B‑1M — part of Blackfrost AI's <b>Void</b> model family. 🖤</em></p>