Instructions to use rafw007/deepseek-v4-flash-fast-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 rafw007/deepseek-v4-flash-fast-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 rafw007/deepseek-v4-flash-fast-GGUF
# Run inference directly in the terminal:
llama cli -hf rafw007/deepseek-v4-flash-fast-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rafw007/deepseek-v4-flash-fast-GGUF
# Run inference directly in the terminal:
llama cli -hf rafw007/deepseek-v4-flash-fast-GGUF

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 rafw007/deepseek-v4-flash-fast-GGUF
# Run inference directly in the terminal:
./llama-cli -hf rafw007/deepseek-v4-flash-fast-GGUF

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 rafw007/deepseek-v4-flash-fast-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rafw007/deepseek-v4-flash-fast-GGUF

Use Docker

docker model run hf.co/rafw007/deepseek-v4-flash-fast-GGUF

LM Studio
Jan

vLLM

How to use rafw007/deepseek-v4-flash-fast-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rafw007/deepseek-v4-flash-fast-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rafw007/deepseek-v4-flash-fast-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rafw007/deepseek-v4-flash-fast-GGUF

Ollama
How to use rafw007/deepseek-v4-flash-fast-GGUF with Ollama:
```
ollama run hf.co/rafw007/deepseek-v4-flash-fast-GGUF
```

Unsloth Studio

How to use rafw007/deepseek-v4-flash-fast-GGUF 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 rafw007/deepseek-v4-flash-fast-GGUF 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 rafw007/deepseek-v4-flash-fast-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rafw007/deepseek-v4-flash-fast-GGUF to start chatting

How to use rafw007/deepseek-v4-flash-fast-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rafw007/deepseek-v4-flash-fast-GGUF

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": "rafw007/deepseek-v4-flash-fast-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use rafw007/deepseek-v4-flash-fast-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rafw007/deepseek-v4-flash-fast-GGUF

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 "rafw007/deepseek-v4-flash-fast-GGUF" \
  --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"

Docker Model Runner
How to use rafw007/deepseek-v4-flash-fast-GGUF with Docker Model Runner:
```
docker model run hf.co/rafw007/deepseek-v4-flash-fast-GGUF
```

Lemonade

How to use rafw007/deepseek-v4-flash-fast-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rafw007/deepseek-v4-flash-fast-GGUF

Run and chat with the model

lemonade run user.deepseek-v4-flash-fast-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use rafw007/deepseek-v4-flash-fast-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 rafw007/deepseek-v4-flash-fast-GGUF

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 rafw007/deepseek-v4-flash-fast-GGUF

Run Hermes

hermes

Atomic Chat

DeepSeek-V4-Flash-Fast

DeepSeek-V4-Flash-Fast is a custom agent build based on DeepSeek-V4-Flash (Open Weights, Apache-2.0, MoE, ~285B total / ~20B active). Weights in low-bit quantization for fully CPU-only deployment:

GGUF: DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf

Not trained from scratch — architecture is 100% DeepSeek-V4-Flash. Agent behaviour is prompt engineering + configuration.

Agent config origin

Tuned with only two models:

Fable5 — stable, timely tool calls, "DO tasks" style.
DeepSeek-V4 — iterating agent loop/config against a real coding agent.

The base system prompt was tuned for the DeepSeek Fast model.

Purpose — agentic tasks (harness)

A native backend that executes real shell commands and answers only from real tool output.

Build goal: a model for weaker machines — to work normally on a 285B model, only ~96 GB of unified memory is required. A big model runs on high-end Mac/RTX-class hardware without costly, dedicated GPU packs.

Prefill focus: agent harness imposes a large prefill. Work focused on increasing prefill throughput (prompt tokens/s).

Testing harnesses

opencode
pi coding agent
claude code

Test machine: GMKtec EVO (x86).

Typical tasks (all passed — real results, no hallucination)

Network scan nmap + interpretation.
Disk usage (df/du) — real numbers.
Remote Linux server inventory — CPU/RAM/disk/OS.
HTML5 Tetris — full working game.
HTML5 solar system — animated orbits.

Runtime params (llama-server / llama-swap)

-t 16 -tb 16 -b 16384 -ub 16384 -c 131072 (128K)
--temp 0.2, --top-p 0.95, --top-k 40, --repeat-penalty 1.15, --presence-penalty 1.0, --reasoning off
--jinja --chat-template-file

Downloads last month: -

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants