Instructions to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF",
	filename="DeepSeek-V4-Flash-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

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 Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

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 Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with Ollama:
```
ollama run hf.co/Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF 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 Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF 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 Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0
```

Lemonade

How to use Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-Q8_0-GGUF-Q8_0

List all available models

lemonade list

DeepSeek-V4-Flash Q8_0 GGUF

Lossless Q8_0 GGUF conversion of deepseek-ai/DeepSeek-V4-Flash (284B params, 13B active).

Use cases

Inference: ~282 GB. Suitable for rigs with combined VRAM ≥ 320 GB (e.g., 4× A100 80GB, 4× H100 80GB, 4× RTX Pro 6000 96GB) using llama.cpp's tensor-parallel paths. Quality is essentially indistinguishable from the original FP8/FP4 source — Q8_0 is the gold-standard "near-lossless" quantization.

Calibration source: serves as the input for downstream IQ-quant generation via llama-quantize --imatrix. If you want to make your own custom quants, this is the right starting point.

Provenance

Converted from the original FP8/FP4 mixed-precision safetensors via convert_hf_to_gguf.py from nisparks/llama.cpp wip/deepseek-v4-support (PR #22378).

Compatibility

Requires llama.cpp built from PR #22378 or later (mainline once merged). The new deepseek4 architecture is not yet in stable releases. See nisparks's branch for build instructions.

Related artifacts

Preyazz/DeepSeek-V4-Flash-GGUF — derived K-quants and (forthcoming) IQ-quants for smaller deployment
Preyazz/DeepSeek-V4-Flash-imatrix — importance matrix for IQ quantization (private)

Downloads last month: 1,803

GGUF

Model size

284B params

Architecture

deepseek4

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(68)

this model

Quantizations

1 model