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

Libraries

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-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 qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

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 qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

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 qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

Use Docker

docker model run hf.co/qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

SGLang

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with Ollama:
```
ollama run hf.co/qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
```
Unsloth Desktop

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

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": "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with Docker Model Runner:
```
docker model run hf.co/qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M
```

Lemonade

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-Vision-Exp-GGUF-IQ1_M

List all available models

lemonade list

Hermes Agent

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-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 qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

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 qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M

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 "qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF:IQ1_M" \
  --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-Vision-Exp-GGUF (Text-Only)

⚠️ Important: Text-Only Quantization

This repository contains text-only GGUF quantizations of DeepSeek-V4-Flash-Vision-Exp.

✅ Full text reasoning capabilities preserved
✅ All 7 quantization levels with PPL validation
✅ Calibrated with high-quality community dataset
❌ Vision encoder not included (image input not supported)

Vision support in GGUF format requires upstream llama.cpp integration, which is still in development. This release focuses on delivering production-ready text quantizations with comprehensive quality validation.

For multimodal capabilities, use the original safetensors model from deepseek-ai/DeepSeek-V4-Flash-Vision-Exp.

Model Details

Property	Value
Base Model	DeepSeek-V4-Flash-Vision-Exp
Architecture	DeepSeek-V4 (256 experts, top-6 routing)
Parameters	256×8.4B (2.1T total, 50.4B active)
Context Length	128K tokens
Quantization	7 levels (Q3_K_M to IQ1_S)
Total Size	616 GiB (28 shards)
License	MIT

Quantization Quality

All quantizations calibrated with high-quality community dataset and validated with perplexity testing.

Baseline (BF16): PPL = 2.3549

Quant	File Size	PPL	Δ%	Use Case
Q3_K_M	130 GB	2.66	+13%	Recommended - Best quality/size balance
IQ3_XXS	106 GB	3.17	+35%	High quality, smaller size
Q2_K	101 GB	3.70	+57%	Balanced compression
IQ2_XS	83 GB	5.22	+122%	Aggressive compression
IQ2_XXS	75 GB	5.95	+153%	Very small size
IQ1_M	65 GB	8.43	+258%	Extreme compression
IQ1_S	59 GB	9.22	+291%	Maximum compression

Quality Notes

Q3_K_M through Q2_K: Production-ready, minimal quality loss
IQ2_XS through IQ2_XXS: Acceptable for most use cases
IQ1_M and IQ1_S: Experimental, noticeable degradation

All models maintain structural integrity with 1328 tensors and 256 experts verified.

How to Use

Requirements

# Latest llama.cpp with DeepSeek-V4 support
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
git checkout master  # Ensure you have DeepSeek-V4 support
make LLAMA_CUDA=1    # or your preferred backend

Basic Inference

# Download a quantization (example: Q3_K_M, 130GB)
huggingface-cli download qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF \
  --include "DeepSeek-V4-Flash-Vision-Exp-Q3_K_M-*" \
  --local-dir ./models

# Run inference
./llama-cli \
  -m models/DeepSeek-V4-Flash-Vision-Exp-Q3_K_M-00001-of-00004.gguf \
  -p "Explain quantum computing in simple terms:" \
  -n 512 \
  -ngl 99  # Offload to GPU

Server Mode

./llama-server \
  -m models/DeepSeek-V4-Flash-Vision-Exp-Q3_K_M-00001-of-00004.gguf \
  -c 4096 \
  -ngl 99 \
  --host 0.0.0.0 \
  --port 8080

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="models/DeepSeek-V4-Flash-Vision-Exp-Q3_K_M-00001-of-00004.gguf",
    n_ctx=4096,
    n_gpu_layers=-1,  # Use GPU
    verbose=False
)

response = llm.create_chat_completion(
    messages=[
        {"role": "user", "content": "Write a Python function to calculate Fibonacci numbers."}
    ],
    max_tokens=512,
    temperature=0.7
)

print(response['choices'][0]['message']['content'])

Hardware Requirements

Quant	VRAM (Estimate)	Recommended GPU
Q3_K_M	~135 GB	2×H100 (80GB) or 2×A100 (80GB)
IQ3_XXS	~110 GB	2×H100 (80GB) or 2×A100 (80GB)
Q2_K	~105 GB	2×H100 (80GB) or 2×A100 (80GB)
IQ2_XS	~86 GB	2×A100 (40GB) or 1×H100 (80GB)
IQ2_XXS	~78 GB	1×H100 (80GB)
IQ1_M	~67 GB	1×A100 (80GB)
IQ1_S	~61 GB	1×A100 (80GB)

Estimates include model weights + KV cache. Actual requirements vary by context length.

Technical Details

Quantization Method

Calibration Dataset: High-quality community dataset (MIT licensed)
Protected Layers:
- Attention: Q8_0
- Shared Experts: Q8_0
- Router/Indexer: Q8_0
- Compressor: Q8_0
- Hyper-Connections: F32
- FFN Gate Input: F32
- Embeddings/Output: Q6_K
Verification: All quantizations validated with tensor count (1328) and expert count (256)

Architecture Highlights

MoE Structure: 256 experts per layer, top-6 routing
Active Parameters: 50.4B per forward pass
Hash Routing: First 3 layers use hash-based expert selection
Hyper-Connections: Cross-layer skip connections for improved training

Changelog

2026-09-04 - Initial release

7 quantization levels (Q3_K_M to IQ1_S)
Text-only conversion with vision tensors filtered
Comprehensive PPL validation
Community calibration dataset

Limitations

No Vision Support: Image inputs are not supported. Text-only inference.
Large Memory Requirements: Even the smallest quant (IQ1_S) requires 61GB VRAM.
Split Files: Models are split into 4 shards due to size. Download all parts.

Citation

@misc{deepseek-v4-flash-vision-exp-gguf,
  title={DeepSeek-V4-Flash-Vision-Exp-GGUF (Text-Only)},
  author={qtum},
  year={2026},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF}}
}

Original model by DeepSeek AI:

@misc{deepseek-v4-flash-vision-exp,
  title={DeepSeek-V4-Flash-Vision-Exp},
  author={DeepSeek AI},
  year={2026},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp}}
}

License

This quantization is released under the MIT License, matching the base model.

About qtum

qtum publishes high-quality GGUF quantizations with transparent quality metrics and open calibration data. All releases include perplexity validation and are tested for structural integrity.

For questions or issues, please open an issue on this repository.

Downloads last month: 2,180

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

1-bit

2-bit

3-bit

Model tree for qtum/DeepSeek-V4-Flash-Vision-Exp-GGUF

Base model

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

Quantized

(24)

this model