# DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

> A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode

- **Organisation:** xtools-at
- **Category:** Chat & Text Generation, Reasoning Models
- **Parameters:** 9.4B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-30
- **Hugging Face:** 27K downloads (30 days), 7.5K likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 4.53 |
| Q3_K_M | 6 |
| Q4_K_M | 7.08 |
| Q5_K_M | 8.04 |
| Q6_K | 9.08 |
| Q8_0 | 11.28 |
| F16 | 19.9 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [SGLang](https://selfhost.directory/project/sglang)
- [Text Generation Inference](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LM Studio](https://lmstudio.ai) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode

🔬 DeepSeek-V4-Pro Distillation 🧠 9B Parameters 📐 ~250K Math & STEM Samples ⚡ MTP & NVFP4 Evaluated

💡 What is DeepSeek-V4-Pro-Qwen3.5-9B? DeepSeek-V4-Pro-Qwen3.5-9B is a reasoning-focused fine-tune of Qwen3.5-9B , distilled from responses generated by DeepSeek-V4-Pro in Max Effect mode . The release concentrates its supervised signal on mathematics and STEM problem solving while preserving the efficiency and practical deployability of the 9B parameter class.

🧩 Structured Reasoning Learns rigorous problem decomposition and multi-step solution patterns from a strong teacher.

📐 Math & STEM Focus Trained on approximately 250,000 samples centered on mathematics and scientific reasoning.

🧪 Cross-Domain Transfer Shows small post-training gains in programming and tool use despite receiving no coding-specific SFT data.

⚙️ Practical Deployment Evaluated through vLLM NVFP4 and llama.cpp MTP-Q8_0 deployment paths.

🧪 Hardware Cooperation & Joint Collaboration

This project is built in close collaboration with hardware engineer Kyle Hessling , whose infrastructure, training support, and evaluation assistance helped make this release possible. 👉 Follow his hardware and model-training updates on X / Twitter: @KyleHessling1

🦥 Fine-tuning Framework (Unsloth)

## Alternatives

- [ornith-ai/Ornith-1.5-9B](https://selfhost.directory/models/ornith-ai/ornith-1.5-9b) (9.7B, MIT, ≈7.22 GB at Q4): Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
- [ornith-ai/Ornith-1.0-9B](https://selfhost.directory/models/ornith-ai/ornith-1.0-9b) (9B, MIT, ≈6.84 GB at Q4): Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
- [Qwen/Qwen3-8B](https://selfhost.directory/models/qwen/qwen3-8b) (8.2B, Apache 2.0, ≈6.48 GB at Q4): Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
- [ibm-granite/granite-4.2-8b](https://selfhost.directory/models/ibm-granite/granite-4.2-8b) (8.8B, Apache 2.0, ≈6.96 GB at Q4): Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.
- [IFM/K2-Horizon-7B](https://selfhost.directory/models/ifm/k2-horizon-7b) (9B, Apache 2.0, ≈6.96 GB at Q4): K2-Horizon-7B is the medium dense member of the K2-Horizon family: a 7B-core decoder-only model with a 512K context window.
- [ibm-granite/granite-4.1-8b](https://selfhost.directory/models/ibm-granite/granite-4.1-8b) (8.8B, Apache 2.0, ≈6.96 GB at Q4): Model Summary: Granite-4.1-8B is a 8B parameter long-context instruct model finetuned from Granite-4.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

More: https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/rtx-4060): Q4_K_M, est. 26 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/apple-m4-16gb): Q6_K, est. 8.5 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/rx-6700-xt): Q8_0, est. 21 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/rtx-3060): Q8_0, est. 20 tok/s
- [Arc B580](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/arc-b580): Q8_0, est. 25 tok/s
- [Tesla T4](https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic/on/tesla-t4): Q8_0, est. 18 tok/s

## Similar size

- [meta-llama/Llama-3.1-8B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.1-8b-instruct) (8B)
- [Qwen/Qwen3-8B](https://selfhost.directory/models/qwen/qwen3-8b) (8.2B)
- [Qwen/Qwen2.5-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-7b-instruct) (7.6B)
- [meta-llama/Meta-Llama-3-8B-Instruct](https://selfhost.directory/models/meta-llama/meta-llama-3-8b-instruct) (8B)
- [google/gemma-2-9b-it](https://selfhost.directory/models/google/gemma-2-9b-it) (9.2B)
- [mistralai/Mistral-7B-Instruct-v0.2](https://selfhost.directory/models/mistralai/mistral-7b-instruct-v0.2) (7.2B)

## FAQ

**How much VRAM does DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic need?**
About 7.1 GB at Q4_K_M with an 8K context. Q8_0 needs about 11 GB and full precision about 20 GB. Longer contexts need more memory for the KV cache.

**Can DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic run on the RTX 4060?**
Yes. It fits at Q4_K_M (about 7.2 GB), at an estimated 26 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q4_K_M. With llama.cpp: llama-server -hf mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
- demo: https://huggingface.co/spaces/KyleHessling1/starskip

---
Source: https://selfhost.directory/models/xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic