Instructions to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-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 MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

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 MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

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 MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

Use Docker

docker model run hf.co/MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

LM Studio
Jan
Ollama
How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with Ollama:
```
ollama run hf.co/MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
```
Unsloth Desktop

How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

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": "MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with Docker Model Runner:
```
docker model run hf.co/MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16
```

Lemonade

How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-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 MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

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 MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16

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 "MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF:BF16" \
  --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"

Llamacpp imatrix Quantization of DeepSeek-V4-Flash-Vision-Uncensored by orcarouter

Using llama.cpp release b10809 for quantization.

Original model: https://huggingface.co/orcarouter/DeepSeek-V4-Flash-Vision-Uncensored

Quant details

This is a 3.87bpw quant meant to be run on a 128GB RAM machine with at least 16, or more likely 24GB VRAM GPU. ffn_(?:gate|up)_exps were quantized from MXFP4 down to Q3_K with the rest of the weights being intact, similar to orcarouter's MXFP4 GGUF quant. The idea of using Q3_K over IQ3_S is to win some speed. IQ quants are known to be slower, especially when used with CPU, though the extent of it varies. On my machine exactly the same quant but with IQ3_S layers instead of Q3_K runs ~30% slower in terms of decode speed. In this particular case, the difference in efficiency between the two is negligible: both scale down to 880 MiB and seem to be similar in quality.
The following imatrix was used to create this quant, provided by one of llama.cpp maintainers, tarruda.
Abliteration left the vision tower intact, so it's okay to use any vision tower compatible with the original Vision-Exp model. BF16 was provided in this repo just in case.

If you're looking for a quant that shares the same recipe and idea behind it, but for the original weights (without abliteration), then there's this quant by ddh0.

Downloads last month: 583

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

Inference Providers NEW

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

Model tree for MetaphoricalCode/DeepSeek-V4-Flash-Vision-Uncensored-3.87bpw-Q3_K-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Finetuned

orcarouter/DeepSeek-V4-Flash-Vision-Uncensored

Quantized

(3)

this model