Instructions to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S 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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
# Run inference directly in the terminal:
./llama-cli -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

Use Docker

docker model run hf.co/him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

LM Studio
Jan
Ollama
How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with Ollama:
```
ollama run hf.co/him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
```

Unsloth Studio

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S 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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S 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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S to start chatting

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with Docker Model Runner:
```
docker model run hf.co/him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S
```

Lemonade

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-DSpark-draft-Q3_K_S-Q3_K_S

List all available models

lemonade list

Hermes Agent

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

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 him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S

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 "him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S:Q3_K_S" \
  --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"

DeepSeek V4 Flash DSpark Draft — Q3_K_S

Q3_K_S quantized DSpark draft model for DeepSeek V4 Flash, for use with speculative decoding (DSpark).

Origin

Source: the DSpark drafter shipped in unsloth/DeepSeek-V4-Flash-0731-GGUF (Q8_0)
Requantized to Q3_K_S with llama-quantize --allow-requantize
Size: 8.54 GB

Usage

Use as the draft model together with a DeepSeek V4 Flash main model to accelerate generation.

llama.cpp

llama-server \
  -m <main-model>.gguf \
  --model-draft DeepSeek-V4-Flash-DSpark-draft-Q3_K_S.gguf \
  --spec-type draft-dspark \
  --spec-draft-n-max 2 \
  --spec-draft-type-k q8_0 \
  --spec-draft-type-v q8_0

ds4 (antirez/ds4)

./ds4 -m <main-model>.gguf --rocm --dspark --mtp DeepSeek-V4-Flash-DSpark-draft-Q3_K_S.gguf

Notes

Q3_K_S is much smaller than the Q8_0 source drafter (~8.5 GB vs ~10 GB) at the cost of slightly lower draft quality / acceptance rate. Benchmark before committing on your hardware.
The draft model does not need to be the same quant as the main model.

License

MIT — same as upstream unsloth/DeepSeek-V4-Flash-0731-GGUF.

Credits

unsloth — original DSpark drafter
antirez/ds4 — DSpark engine
Kevletesteur — Strix Halo verified GGUF setup that motivated this requantization

Downloads last month: 71

GGUF

Model size

20B params

Architecture

dflash

Hardware compatibility

3-bit

Inference Providers NEW

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

Model tree for him0413/DeepSeek-V4-Flash-DSpark-draft-Q3_K_S

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

unsloth/DeepSeek-V4-Flash-0731-GGUF

Quantized

(3)

this model