Instructions to use ivanfioravanti/deepseek-v4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ivanfioravanti/deepseek-v4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ivanfioravanti/deepseek-v4-gguf",
	filename="DeepSeek-V4-Flash-Layers10-30-39-42Q4KExperts-OtherExpertLayersQ2-imatrix.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf
# Run inference directly in the terminal:
llama cli -hf ivanfioravanti/deepseek-v4-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ivanfioravanti/deepseek-v4-gguf
# Run inference directly in the terminal:
llama cli -hf ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf
# Run inference directly in the terminal:
./llama-cli -hf ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ivanfioravanti/deepseek-v4-gguf

Use Docker

docker model run hf.co/ivanfioravanti/deepseek-v4-gguf

LM Studio
Jan
Ollama
How to use ivanfioravanti/deepseek-v4-gguf with Ollama:
```
ollama run hf.co/ivanfioravanti/deepseek-v4-gguf
```

Unsloth Studio

How to use ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use ivanfioravanti/deepseek-v4-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ivanfioravanti/deepseek-v4-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": "ivanfioravanti/deepseek-v4-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ivanfioravanti/deepseek-v4-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ivanfioravanti/deepseek-v4-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 "ivanfioravanti/deepseek-v4-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 ivanfioravanti/deepseek-v4-gguf with Docker Model Runner:
```
docker model run hf.co/ivanfioravanti/deepseek-v4-gguf
```

Lemonade

How to use ivanfioravanti/deepseek-v4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ivanfioravanti/deepseek-v4-gguf

Run and chat with the model

lemonade run user.deepseek-v4-gguf-{{QUANT_TAG}}

List all available models

lemonade list

DeepSeek V4 Flash — mixed Q2/Q4 GGUF

Mixed-quantization GGUF for the DS4 runtime.

Quantization recipe

Q4_K routed experts in layers 10, 30, and 39–42.
Other routed-expert layers use the Q2 imatrix recipe: IQ2_XXS gate/up and Q2_K down tensors.
Attention projections, shared experts, and output tensors follow the DS4 Q2-imatrix template.
Six of 43 layers use Q4 routed experts (13.95%).
File size: 97,591,747,456 bytes (90.89 GiB).

The selected Q4 tensors were copied byte-for-byte from the compatible Q4-imatrix GGUF. Other tensors remain byte-identical to the Q2-imatrix base.

Evaluation

All variants below were scored on the same 100 official DeepSeek V4 Flash continuations containing 2,289 target tokens.

Model / routed-expert recipe	Size	Average NLL ↓	NLL vs Q2	Wins vs Q2	First-token matches ↑	Average greedy LCP ↑
Q2 imatrix baseline	80.76 GiB	0.368177401	—	—	63 / 100	5.96
Antirez mixed recipe: Q4 layers `37–42`	90.89 GiB	0.340543836	-7.506%	67 / 33	68 / 100	6.90
This model: Q4 layers `10`, `30`, `39–42`	90.89 GiB	0.338330454	-8.107%	73 / 27	68 / 100	7.47
Full Q4 imatrix	153.33 GiB	0.173978006	-52.746%	87 / 13	86 / 100	12.88

Lower NLL is better. First-token matches count how often greedy generation starts with the same token as the official continuation. Greedy LCP is the number of consecutive matching tokens before the first divergence, so higher is better.

At the same 90.89 GiB size as the Antirez six-layer recipe, this configuration improved NLL, preserved the same first-token match count, and increased average greedy LCP from 6.90 to 7.47.

Usage

./ds4 \
  -m DeepSeek-V4-Flash-Layers10-30-39-42Q4KExperts-OtherExpertLayersQ2-imatrix.gguf \
  --ctx 4096 \
  -p "Hello"

This GGUF uses DS4-specific DeepSeek V4 tensor naming and mixed routed-expert quantization.

Downloads last month: 309

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for ivanfioravanti/deepseek-v4-gguf

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(99)

this model