Instructions to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX 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 julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
# Run inference directly in the terminal:
llama cli -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
# Run inference directly in the terminal:
llama cli -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

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 julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
# Run inference directly in the terminal:
./llama-cli -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

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 julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Use Docker

docker model run hf.co/julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

LM Studio
Jan

vLLM

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Ollama
How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with Ollama:
```
ollama run hf.co/julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
```
Unsloth Desktop

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

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": "julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with Docker Model Runner:
```
docker model run hf.co/julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
```

Lemonade

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-0731-IQ2XXS-STRIX-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

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 julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

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 "julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX" \
  --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-IQ2XXS-STRIX

Quantized DeepSeek V4 Flash (0731) GGUF for AMD Strix Halo (gfx1151).

Details

Base model: DeepSeek V4 Flash 0731 (284B MoE)
Quantization source: tekosML (DeepSeek-V4-Flash-0731-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-imatrix)
File size: 86.72 GB
Architecture: 43 routed layers, 256 experts/layer (6 active), 4-stream hyper-connections

Quant Recipe

Tensor group	Type
Attention projections	Q8_0
Shared experts	Q8_0
Output head	Q8_0
Token embedding	F16
Routed gate/up experts	IQ2_XXS
Routed down experts	Q2_K

Recommended Runtime

Run with the julianmb/ds4fa engine on 128 GB Strix Halo:

DS4_ROCM_STREAM_MODEL_CACHE_GB=48 ./ds4 -m DeepSeek-V4-Flash-0731-IQ2XXS-STRIX.gguf -c 512 \
  --ssd-streaming --ssd-streaming-cache-experts 32GB \
  -p "What is the capital of France?" --think --tokens 60

Downloads last month: 184

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(193)

this model