Instructions to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
# Run inference directly in the terminal:
llama cli -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
# Run inference directly in the terminal:
llama cli -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Use Docker

docker model run hf.co/nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

LM Studio
Jan
Ollama
How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Ollama:
```
ollama run hf.co/nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
```

Unsloth Studio

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding to start chatting

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Docker Model Runner:
```
docker model run hf.co/nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0
```

Lemonade

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Run and chat with the model

lemonade run user.Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding-Q8_0

List all available models

lemonade list

Hermes Agent

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding / README.md

nerkyor

add main model card

8535cd1 verified about 2 months ago

4.78 kB

license: other
language:
  - en
  - zh
tags:
  - qwen3.6
  - dsv4pro
  - glm
  - sft
  - rl
  - coding
  - gguf
  - fp8
  - mtp
base_model: Merkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill

Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding

This is the Hugging Face main repository for the 27B dense coding model.

BF16 weights are stored at the repository root.
GGUF artifacts are stored under GGUF/, copied from the standalone GGUF repository.
FP8 artifacts are stored under FP8/ when synced.
Standalone GGUF repository: nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding-GGUF

The model is based on Merkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill and was further trained for executable coding, repair loops, final-answer discipline, and robust verification behavior.

Repository Layout

Path	Content
root	BF16 safetensors, config, tokenizer and chat template
`GGUF/Q8_0/`	Q8 GGUF baseline, official MTP draft sidecar, eval summaries and manifest
`GGUF/Q5_LynnStyle/`	32GB recommended GGUF quantization, LynnStyle Dense protection rules and eval summaries
`GGUF/Q4_LynnStyle/`	24GB GGUF quantization, LynnStyle Dense protection rules and eval summaries
`FP8/`	ModelOpt FP8 weights, SGLang script, MTP/NEXTN smoke and TPS data

GGUF files are multi-shard models. Load the first shard; llama.cpp will load the remaining shards from the same directory.

llama.cpp GGUF Example

llama-server \
  -m GGUF/Q5_LynnStyle/Q5-imatrix-MTP-00001-of-00004.gguf \
  -ngl 999 --split-mode layer \
  -c 32768 -b 1024 -ub 256 -np 4 -cb \
  --host 0.0.0.0 --port 8080 \
  --jinja --reasoning on --reasoning-format deepseek

Optional speculative decoding with the MTP draft sidecar:

llama-server \
  -m GGUF/Q5_LynnStyle/Q5-imatrix-MTP-00001-of-00004.gguf \
  --model-draft GGUF/Q5_LynnStyle/Q5-imatrix-MTP-draft.gguf \
  -ngl 999 --split-mode layer \
  -c 32768 -b 1024 -ub 256 -np 4 -cb \
  --host 0.0.0.0 --port 8080 \
  --jinja --reasoning on --reasoning-format deepseek

For Q4 on 24GB GPUs, long-context use should prioritize the main model and KV cache. Only load the MTP sidecar for short-context, low-concurrency runs with enough spare VRAM.

FP8 / SGLang

Recommended default: no MTP. MTP/NEXTN is supported but did not improve throughput in the current short-output smoke setup.

bash FP8/scripts/sglang_fp8_start.sh
MTP=1 bash FP8/scripts/sglang_fp8_start.sh

Measured on RTX PRO 6000 Blackwell Server Edition with SGLang 0.5.14, context 16384, 8 short coding requests per mode:

Config	C1	C2	C4
no-MTP	20.7581 tok/s	32.6418 tok/s	61.8252 tok/s
MTP/NEXTN n=2, draft tokens=3	18.3805 tok/s	26.1985 tok/s	47.0971 tok/s

Q8 Clean Reference Scores

FP8 quality scores have not been independently rerun. For FP8, the table below is a Q8 clean-score reference for the same training branch.

Benchmark	Score
MMLU500	462/500 = 92.4%
GPQA198	162/198 = 81.82%
LBC100	78/100
Coding100 current clean	88/100

Quantized Clean Results

Version	MMLU500	GPQA198	LBC100	Coding100
Q8	92.4%	81.82%	78/100	88/100
Q5 LynnStyle	92.2%	78.79%	75/100	not rerun
Q4 LynnStyle	92.0%	74.75%	71/100	82/100

Clean-gate policy: harness pollution, server-not-ready rows, parse failures caused by infrastructure, partial rows, and connection failures are not counted as model errors.

LynnStyle Dense Quantization

This 27B model is dense, not MoE. LynnStyle Dense quantization protects critical layer positions, full-attention layers, attention gates, SSM tensor families, and selected tensor families while compressing ordinary regions more aggressively. Low-bit releases use explicit protection plus imatrix or equivalent importance calibration.

中文说明

这是 27B Dense 编程模型的 Hugging Face 主仓。

根目录放 BF16 权重。
GGUF/ 放从 GGUF 独立仓复制过来的 Q8/Q5/Q4/Q3 等 GGUF 运行产物。
FP8/ 放 FP8 权重、SGLang 启动脚本和 TPS/MTP smoke 数据。
GGUF 独立仓：nerkyor/Qwen3.6-27B-DSV4Pro-GLM52-SFT-GPT55-RL-Coding-GGUF

本模型基于 Merkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill 继续后训练，重点强化可执行代码、闭环修复、验证纪律、final-answer 可靠性和推理预算控制。

GGUF 多分片模型只需要指定第一片；MTP sidecar 是可选 speculative decoding 加速件，不是主模型。FP8 默认推荐 no-MTP；当前短输出压测下 no-MTP TPS 高于 MTP/NEXTN。