Instructions to use Volko76/DeepSeek-V4-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Volko76/DeepSeek-V4-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Volko76/DeepSeek-V4-Flash-GGUF",
	filename="DeepSeek-V4-Flash-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Volko76/DeepSeek-V4-Flash-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

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 Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

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 Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

Use Docker

docker model run hf.co/Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use Volko76/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 "Volko76/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": "Volko76/DeepSeek-V4-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

Ollama
How to use Volko76/DeepSeek-V4-Flash-GGUF with Ollama:
```
ollama run hf.co/Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
```

Unsloth Studio new

How to use Volko76/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 Volko76/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 Volko76/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 Volko76/DeepSeek-V4-Flash-GGUF to start chatting

Pi new

How to use Volko76/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-server -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

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": "Volko76/DeepSeek-V4-Flash-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Volko76/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-server -hf Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

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 Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

Run Hermes

hermes

Docker Model Runner
How to use Volko76/DeepSeek-V4-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/Volko76/DeepSeek-V4-Flash-GGUF:Q2_K
```

Lemonade

How to use Volko76/DeepSeek-V4-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Volko76/DeepSeek-V4-Flash-GGUF:Q2_K

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-GGUF-Q2_K

List all available models

lemonade list

DeepSeek-V4-Flash-GGUF / README.md

Volko76

Update README.md

5f45ca7 verified 6 days ago

preview code

raw

history blame contribute delete

2.81 kB

metadata

base_model: deepseek-ai/DeepSeek-V4-Flash
base_model_relation: quantized
library_name: llama.cpp
license: mit
pipeline_tag: text-generation
tags:
  - gguf
  - llama.cpp
  - deepseek_v4
  - text-generation
  - conversational
  - en
  - license:mit
  - endpoints_compatible
  - region:us
  - base_model:deepseek-ai/DeepSeek-V4-Flash
  - base_model:quantized:deepseek-ai/DeepSeek-V4-Flash
  - endpoints_compatible
  - region:us

A Q2_K version of https://huggingface.co/ssweens/deepseek-ai__DeepSeek-V4-Flash-GGUF-YMMV

🧪 Experimental GGUFs for DeepSeek-V4-Flash

A stopgap to experiment with DeepSeek-V4-Flash with CUDA and ROCm locally while the tools ecosystem catches up. Expect rough edges. Validated for text and coding coherence.

GGUF files for deepseek-ai/DeepSeek-V4-Flash.

⚠️ You need the custom fork

These GGUFs require a DeepSeek-V4-capable fork of llama.cpp. Vanilla llama.cpp doesn't support this architecture yet.

llama.cpp fork: ssweens/llama.cpp-deepseek-v4
Backends: Tested on CUDA and ROCm.

Performance

Example:

llama-server -ngl 99 --no-mmap -fa on -np 1 --reasoning-format auto --jinja --threads 3 -ts 4,4,3 -dev CUDA0,CUDA1,CUDA2 \
-m /mnt/supmodels/gguf/deepseek-ai__DeepSeek-V4-Flash/deepseek-ai__DeepSeek-V4-Flash-Q4_K_M.gguf -c 32768 -b 2048 -ub 512 -ctk q8_0 -ctv q8_0

Speed (custom, n=2)

Model	Prompt t/s	Gen t/s	TTFT s	Decode s	Backend
IQ2_XXS	389.56	24.04	7.59	0.00	CUDA
Q2_K_S	231.15	18.79	10.58	0.00	CUDA+ROCm
BF16	158.58	10.07	18.17	0.00	CUDA+ROCm
Coding (humaneval_instruct, n=30)
Model	pass@1	Backend
-----	------	-------
IQ2_XXS	0.967±0.033	CUDA
Q2_K_S	0.900±0.056	CUDA+ROCm
BF16	1.000±0.000	CUDA+ROCm

Original model

deepseek-ai/DeepSeek-V4-Flash

Thanks

antirez — llama.cpp fork for Metal and CUDA in llama.cpp-deepseek-v4-flash
ml-explore/mlx-lm #1192 — MLX DSV4 attention reference that informed the architecture work
DeepSeek — open inference code and the technical report
nisparks et al - some early implementation efforts and discussion
llama.cpp — the project that makes local LLM inference possible