Instructions to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF with Ollama:
```
ollama run hf.co/heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-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": "heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF with Docker Model Runner:
```
docker model run hf.co/heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M
```

Lemonade

How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-0731-REAP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use heath0xFF/DeepSeek-V4-Flash-0731-REAP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf heath0xFF/DeepSeek-V4-Flash-0731-REAP-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 "heath0xFF/DeepSeek-V4-Flash-0731-REAP-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"

DeepSeek-V4-Flash-0731-REAP-GGUF / README.md

Dumbledore2

Update README.md

e26dbd3 verified about 2 months ago

1.58 kB

license: mit
library_name: gguf
tags:
  - deepseek
  - deepseek-v4
  - deepseek-v4-flash
  - moe
  - reap
  - gguf
  - mxfp4

DeepSeek-V4-Flash-0731-REAP-K160-GGUF

GGUF quantizations of 0xSero/DeepSeek-V4-Flash-0731-REAP — a REAP expert-pruned DeepSeek-V4-Flash checkpoint retaining 160 of 256 routed experts per MoE layer.

Base model: 0xSero/DeepSeek-V4-Flash-0731-REAP
Original model: deepseek-ai/DeepSeek-V4-Flash-0731
Format: GGUF
Total params: ~193B
Routed experts: 160 per layer (REAP-pruned from 256)
Architecture: deepseek4

Variants

File	Quant	Size	Description
DeepSeek-V4-Flash-0731-REAP-K160-MXFP4.gguf	MXFP4 (native)	95 GB	Direct conversion, experts at native 4-bit precision
DeepSeek-V4-Flash-0731-REAP-K160-Q4_K_M.gguf	Q4_K_M	102 GB	K-quant mixing (Q4_K / Q6_K)
DeepSeek-V4-Flash-0731-REAP-K160-Q2_K.gguf	Q2_K	~65 GB	Compact variant for low-memory hardware

Serving

These GGUFs use the deepseek4 architecture. Compatible runtimes:

DwarfStar (ds4) — reference engine, supports MXFP4 native format
llama.cpp — with GGML_CUDA=ON for GPU support

License

MIT — inherited from the base model.

Acknowledgements

DeepSeek for the base model
0xSero for the REAP pruning
Cerebras Research for REAP
llama.cpp contributors
antirez for DwarfStar