Instructions to use neureps/warmly-qwen35-2b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use neureps/warmly-qwen35-2b-gguf 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 neureps/warmly-qwen35-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

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 neureps/warmly-qwen35-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

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 neureps/warmly-qwen35-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

Use Docker

docker model run hf.co/neureps/warmly-qwen35-2b-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use neureps/warmly-qwen35-2b-gguf with Ollama:
```
ollama run hf.co/neureps/warmly-qwen35-2b-gguf:Q4_K_M
```
Unsloth Desktop

How to use neureps/warmly-qwen35-2b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

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": "neureps/warmly-qwen35-2b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use neureps/warmly-qwen35-2b-gguf with Docker Model Runner:
```
docker model run hf.co/neureps/warmly-qwen35-2b-gguf:Q4_K_M
```

Lemonade

How to use neureps/warmly-qwen35-2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neureps/warmly-qwen35-2b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.warmly-qwen35-2b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use neureps/warmly-qwen35-2b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

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 neureps/warmly-qwen35-2b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use neureps/warmly-qwen35-2b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf neureps/warmly-qwen35-2b-gguf:Q4_K_M

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 "neureps/warmly-qwen35-2b-gguf:Q4_K_M" \
  --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"

Warmly — Qwen3.5-2B GGUF (Korean-calibrated imatrix)

1인용 오프라인 SNS 앱 **온기(Warmly)**의 온디바이스 댓글 생성 모델입니다. Qwen/Qwen3.5-2B를 한국어 SNS 댓글 도메인 텍스트(영어 캡션 + 한국어 페르소나 댓글 372샘플)로 캘리브레이션한 imatrix로 Q4_K_M 양자화했습니다. MTP 레이어는 제거(--no-mtp)했습니다.

파일	크기	용도
`Qwen3.5-2B-Q4_K_M.gguf`	~1.2GB	텍스트 생성 (캡션→댓글, 답글)
`mmproj-Q8_0.gguf`	~348MB	비전 프로젝터 (이미지→캡션)
`imatrix.dat` / `calib.txt`	—	재현용 캘리브레이션 산출물

실측 (2026-07-13, 사진 5장 × 페르소나 4명)

자연스러운 한국어 댓글: ~15/20 (F16 ~16/20, 일반 Q4_K_M ~12-13/20)
mmproj Q8_0은 F16 대비 캡션 출력이 단어 단위로 동일 (greedy 비교)
Qwen3.5는 enable_thinking: false 필수 (미지정 시 전 토큰이 reasoning으로 소모)

사용

llama-server -m Qwen3.5-2B-Q4_K_M.gguf --mmproj mmproj-Q8_0.gguf --port 8081

Downloads last month: 28

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for neureps/warmly-qwen35-2b-gguf

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Quantized

(242)

this model