DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Instructions to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF")
model = AutoModelForCausalLM.from_pretrained("AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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 AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
# Run inference directly in the terminal:
llama cli -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
# Run inference directly in the terminal:
llama cli -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

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 AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
# Run inference directly in the terminal:
./llama-cli -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

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 AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Use Docker

docker model run hf.co/AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

LM Studio
Jan

vLLM

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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": "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

SGLang

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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 "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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": "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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": "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with Ollama:
```
ollama run hf.co/AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
```
Unsloth Desktop

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

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": "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with Docker Model Runner:
```
docker model run hf.co/AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF
```

Lemonade

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-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 AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

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 AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

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 "AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF" \
  --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"

NOESIS / AMAImedia

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

Founder: Ilia Bolotnikov
Organization: AMAImedia.com
X (Twitter): @AMAImediacom
LinkedIn: Ilia Bolotnikov
Telegram: @djbionicl
Release date: 2026-08-31

AMAImedia

Released and maintained by AMAImedia.

Original repository: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

DeepSeek-V4-Flash-Vision-Exp

Introduction

We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

Compared to DeepSeek-V4-Flash-0731, DeepSeek-V4-Flash-Vision-Exp achieves substantial improvements on its multimodal agent capabilities, while maintaining comparable performance on text-only agent tasks.

Benchmark	DeepSeek-V4-Flash-Vision-Exp	DeepSeek-V4-Flash-0731	Opus-4.8
Text Agent Capabilities
Terminal Bench 2.1	83.9	82.7	85.0
NL2Repo	57.7	54.2	69.7
Cybergym	75.3	76.7	78.3
DeepSWE	59.3	54.4	58.0
Toolathlon-Verified	75.9	70.3	76.2
DSBench-Hard	63.6	59.6	71.7
AutomationBench (Public)	25.7	25.1	27.2
Multimodal Agent Capabilities
ApexBench (Pass@1)	36.5	26.2†	39.4
Agents' Last Exam	27.3	25.2†	25.7
Chartography	64.3	-	65.0
ZeroBench (Pass@5)	35.0	-	34.0

Notes:

For the text agent benchmarks above, DeepSeek models are evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning effort level with temperature = 1.0, top_p = 0.95.
† For ApexBench and Agents' Last Exam, DeepSeek-V4-Flash-0731 ignores the multimodal elements in the input.

Repository layout

This repository contains the tokenizer, prompt encoding reference, and a minimal PyTorch inference implementation for DeepSeek-V4 Flash Vision. The reference inference covers the vision encoder and aligner, DFlash attention, MoE, Hyper-Connections, and the DSpark forward path.

.
├── encoding/                  # OpenAI-style messages -> model prompt
├── inference/                 # weight conversion and minimal inference
│   └── examples/              # equivalent TXT and JSON vision prompts
├── config.json                # Hugging Face model metadata
├── generation_config.json
├── model.safetensors.index.json
├── tokenizer.json
└── tokenizer_config.json

encoding/ and inference/ deliberately remain separate: prompt formatting does not depend on PyTorch, while inference imports the sibling encoding module with an explicit Python path. No symlinks are required.

The tokenizer files are regular files so that the repository can be uploaded to Hugging Face without relying on local filesystem symlinks. The large model shards are described by model.safetensors.index.json and are not duplicated inside the source checkout used to assemble this repository.

Prompt encoding

See encoding/README.md. Both OpenAI-style JSON content blocks and the compact <image>path</image> TXT notation are supported. The two examples under inference/examples/ encode to identical prompts and token IDs.

Minimal inference

See inference/README.md for dependency installation, checkpoint conversion, and TXT/JSON inference commands.

How to Run with vLLM

For example, the command below serves the model with vLLM on a single 4×GB300 node. See the vLLM recipe for detailed instructions and other hardware configurations.

docker run --gpus all \
  vllm/vllm-openai:deepseekv4-flash-vision deepseek-ai/DeepSeek-V4-Flash-Vision-Exp \
  --kv-cache-dtype fp8 \
  --block-size 256 \
  --tensor-parallel-size 4 \
  --tool-call-parser deepseek_v4 \
  --enable-auto-tool-choice \
  --reasoning-parser deepseek_v4 \
  --reasoning-config '{"reasoning_parser":"deepseek_v4","reasoning_start_str":"","reasoning_end_str":""}' \
  --speculative-config '{"method":"dspark","model":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","num_speculative_tokens":3,"draft_sample_method":"probabilistic","enable_adaptive_verification":true}'

How to Run with SGLang

Enable DSpark with --speculative-algorithm DSPARK and do not set a separate --speculative-draft-model-path as the target and draft weights therefore come from the same checkpoint. See the SGLang cookbook for detailed instructions, benchmarks and other hardwares configurations.

sglang serve \
  --model-path deepseek-ai/DeepSeek-V4-Flash-Vision-Exp \
  --tp 4 \
  --speculative-algorithm DSPARK \
  --mem-fraction-static 0.85 \
  --host 0.0.0.0 \
  --port 30000

License

This repository is licensed under the MIT License.

Downloads last month: 410

Safetensors

Model size

305B params

Tensor type

BF16

F32

F8_E4M3

I64

Collection including AMAImedia/DeepSeek-V4-Flash-Vision-Exp-FP8-GGUF

Hy4-GLM5.3-KimiK3-DeepSeek4-Qwen3.8

Collection

14 items • Updated 1 day ago