Instructions to use tarruda/DeepSeek-V4-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tarruda/DeepSeek-V4-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tarruda/DeepSeek-V4-Flash-GGUF",
	filename="IQ3_XXS/DeepSeek-V4-Flash-IQ3_XXS-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tarruda/DeepSeek-V4-Flash-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 tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama cli -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama cli -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

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 tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./llama-cli -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

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 tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

Use Docker

docker model run hf.co/tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

LM Studio
Jan

vLLM

How to use tarruda/DeepSeek-V4-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tarruda/DeepSeek-V4-Flash-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": "tarruda/DeepSeek-V4-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

Ollama
How to use tarruda/DeepSeek-V4-Flash-GGUF with Ollama:
```
ollama run hf.co/tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
```

Unsloth Studio

How to use tarruda/DeepSeek-V4-Flash-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 tarruda/DeepSeek-V4-Flash-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 tarruda/DeepSeek-V4-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use tarruda/DeepSeek-V4-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

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": "tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tarruda/DeepSeek-V4-Flash-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 tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

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 tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use tarruda/DeepSeek-V4-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS
```

Lemonade

How to use tarruda/DeepSeek-V4-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tarruda/DeepSeek-V4-Flash-GGUF:IQ3_XXS

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-GGUF-IQ3_XXS

List all available models

lemonade list

DeepSeek V4 Flash GGUF

GGUF quantizations for deepseek-ai/DeepSeek-V4-Flash

DeepSeek published the original model weights in MXFP4, so the MXFP4 GGUFs in this repo are direct conversions of those original safetensors.

Quant Recipes

Recipe	Quant Size	Default type	Tensor-specific overrides
`Q3_K`	119297.23 MiB (3.52 BPW)	`Q6_K`	`ffn_down_exps=q3_k`, `ffn_gate_exps=q3_k`, `ffn_up_exps=q3_k`
`IQ3_XXS`	106912.23 MiB (3.15 BPW)	`Q6_K`	`ffn_down_exps=iq3_xxs`, `ffn_gate_exps=iq3_xxs`, `ffn_up_exps=iq3_xxs`
`Q2_K`	92465.23 MiB (2.73 BPW)	`Q6_K`	`ffn_down_exps=q2_k`, `ffn_gate_exps=q2_k`, `ffn_up_exps=q2_k`

Usage

This is the script I use to run:

#!/bin/sh -e

model="./IQ3_XXS/DeepSeek-V4-Flash-IQ3_XXS-00001-of-00004.gguf"

ctx=131072
parallel=1

ctx_size=$((ctx * parallel))

llama-server --no-mmap --no-warmup \
  --model $model --ctx-size $ctx_size -np $parallel \
  --temp 1.0 --top-p 1.0

Downloads last month: -

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

2-bit

3-bit

View +2 variants

Model tree for tarruda/DeepSeek-V4-Flash-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(84)

this model