Instructions to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4",
	filename="DeepSeek-V4-Flash-REAP25-LCB50-DS4-compact-IQ2XXS.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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
# Run inference directly in the terminal:
llama-cli -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
# Run inference directly in the terminal:
llama-cli -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
# Run inference directly in the terminal:
./llama-cli -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

Use Docker

docker model run hf.co/eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

LM Studio
Jan

vLLM

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

Ollama
How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with Ollama:
```
ollama run hf.co/eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
```

Unsloth Studio new

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 to start chatting

Pi new

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

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": "eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

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 eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

Run Hermes

hermes

Docker Model Runner
How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with Docker Model Runner:
```
docker model run hf.co/eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4
```

Lemonade

How to use eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eouya2/DeepSeek-V4-Flash-REAP25-LCB50-DS4

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-REAP25-LCB50-DS4-{{QUANT_TAG}}

List all available models

lemonade list

DeepSeek-V4-Flash REAP25 LCB50 DS4 GGUF

Experimental DS4 compact GGUF made by applying 25% REAP expert pruning to a DeepSeek-V4-Flash DS4 GGUF.

Model file:

DeepSeek-V4-Flash-REAP25-LCB50-DS4-compact-IQ2XXS.gguf

Bundled runtime:

ds4_reap_runtime/

Compatibility

This model needs the bundled REAP-aware DS4 runtime, or another DS4 build that supports ds4-compact-v1.

It is not expected to run with stock DS4, llama.cpp, Ollama, LM Studio, or other generic GGUF loaders. The routed expert tensors are physically compacted, so the runtime must read the REAP metadata and route into compact expert ids.

Expected DS4 runtime line:

REAP runtime metadata enabled: hash_preserved=3 router_masked=40 moe_disabled=0 layout=ds4-compact-v1

How It Was Made

Source GGUF:

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

Calibration:

Dataset: LiveCodeBench
Selected samples: 50
Sampling: balanced random by difficulty
Seed: 42
Distribution: easy 17, medium 17, hard 16
Observed prompt tokens: 26386
Observed routed expert selections: 6807588

Pruning:

Layers 0-2: preserved, hash-routed
Layers 3-42: REAP-pruned
Compression ratio: 0.25
Experts per pruned layer: 256 -> 192
Top-k remains 6
Expert tensor bytes are copied directly, preserving source quantization

Size:

source file: 80.76 GiB / 86.72 GB
REAP25 file: 63.87 GiB / 68.58 GB

Local Metal mapping at --ctx 512:

source mapped: 82697.67 MiB
REAP25 mapped: 65397.66 MiB
saved: ~17300 MiB, about 16.9 GiB

Run With Bundled Runtime

The Metal runtime loads shader source files from metal/*.metal, so run from inside the bundled runtime directory:

cd ds4_reap_runtime

./ds4 \
  -m ../DeepSeek-V4-Flash-REAP25-LCB50-DS4-compact-IQ2XXS.gguf \
  --ctx 512 --nothink --temp 0 -n 64 \
  -p 'stack and queue python code'

For OpenAI-compatible local serving:

cd ds4_reap_runtime

./ds4-server \
  -m ../DeepSeek-V4-Flash-REAP25-LCB50-DS4-compact-IQ2XXS.gguf \
  --ctx 32768 --tokens 1024 \
  --host 127.0.0.1 --port 8000

Notes

This is a 50-sample coding-domain calibration artifact, not a full benchmarked release. It is mainly for testing DS4-native REAP compaction and runtime support.

Downloads last month: 125

GGUF

Model size

220B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants