Instructions to use ioworker0/DeepSeek-V4-Flash-0731-REAP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ioworker0/DeepSeek-V4-Flash-0731-REAP 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 ioworker0/DeepSeek-V4-Flash-0731-REAP
# Run inference directly in the terminal:
llama cli -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ioworker0/DeepSeek-V4-Flash-0731-REAP
# Run inference directly in the terminal:
llama cli -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

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 ioworker0/DeepSeek-V4-Flash-0731-REAP
# Run inference directly in the terminal:
./llama-cli -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

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 ioworker0/DeepSeek-V4-Flash-0731-REAP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

Use Docker

docker model run hf.co/ioworker0/DeepSeek-V4-Flash-0731-REAP

LM Studio
Jan
Ollama
How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with Ollama:
```
ollama run hf.co/ioworker0/DeepSeek-V4-Flash-0731-REAP
```
Unsloth Desktop

How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

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": "ioworker0/DeepSeek-V4-Flash-0731-REAP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with Docker Model Runner:
```
docker model run hf.co/ioworker0/DeepSeek-V4-Flash-0731-REAP
```

Lemonade

How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ioworker0/DeepSeek-V4-Flash-0731-REAP

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

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 ioworker0/DeepSeek-V4-Flash-0731-REAP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ioworker0/DeepSeek-V4-Flash-0731-REAP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ioworker0/DeepSeek-V4-Flash-0731-REAP

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 "ioworker0/DeepSeek-V4-Flash-0731-REAP" \
  --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 REAP — UD-IQ1_S three-tier GGUF

This repository contains three exploratory, physically compacted expert-retention tiers derived from unsloth/DeepSeek-V4-Flash-0731-GGUF UD-IQ1_S at revision 1290dcca3f84612f646fb546fb9e8433c1b339b0.

Each variant keeps all 256 experts in protected hash-routing layers 0–2. Learned router layers 3–42 retain the experts selected by their fixed REAP prune plan:

Variant	Experts retained per learned layer	Files	Total bytes
K224	224	3	73,741,680,224
K192	192	3	64,944,122,464
K160	160	3	56,146,564,704

Load a tier by selecting its first split, for example:

llama-server \
  -m DeepSeek-V4-Flash-0731-REAP-K224-00001-of-00003.gguf \
  -c 262144 -b 2048 -ub 512 -np 1 \
  --kv-offload -fa on -ctk q8_0 -ctv q8_0 -ngl 999

The pinned llama.cpp basis is a1f96d4fc2c9e4101a6666a9d87f547e7e880df6. These GGUFs encode deepseek4.expert_count as a per-layer array and therefore require the supplied patches/llama-cpp-deepseek4-per-layer-experts.patch. The supplied DeepSeek3 tokenizer long-run fix is also recommended. The REAP runtime patch is included for reproducing profiling and runtime-mask experiments.

Verification status

All three compact writers completed with status=passed; their complete receipts and prune plans are published under receipts/ and prune-plans/.
K192 and K224 were actually loaded with 262,144-token context, Q8 K/V cache, Flash Attention, and full GPU offload on an RTX PRO 6000 Blackwell 96GB.
Observed process memory was 70,672 MiB for K192 and 79,006 MiB for K224.
K192 served real requests after load; K224 reached health: ok.
K160 has not yet received an equivalent real-load smoke in this publication.

This is an exploratory three-candidate publication requested before completion of the preregistered Pi/SWE-Lancer evaluation. It is not an RTX_EXPERIMENT_PASSED or formal HF publication acceptance result. Compact-vs- runtime-mask logit/output parity, final quality selection, A100 cold validation, and the formal agent evaluation remain pending. Do not treat smaller storage or VRAM as a demonstrated quality or speed improvement.

See SHA256SUMS for the public GGUF hashes. The original full model is not mirrored or replaced here.