Instructions to use mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0

Use Docker

docker model run hf.co/mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF with Ollama:
```
ollama run hf.co/mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
```

Unsloth Studio

How to use mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-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 mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF with Docker Model Runner:
```
docker model run hf.co/mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0
```

Lemonade

How to use mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF:Q8_0

Run and chat with the model

lemonade run user.DeepSeek-R1-0528-optimized-for-512Gb-GGUF-Q8_0

List all available models

lemonade list

This model is a merge of three differently quantized models from the unsloth/DeepSeek-R1-0528-GGUF repository. Everything except the routed experts comes from Q8_0, while most routed experts come from UD-Q4-XL and 6 more critical block routed experts originate from UD-Q5-XL.

After setting on Mac "sudo sysctl iogpu.wired_limit_mb=516096", my tests show it achieves maximum performance with a 16k context window under this size constraint. A 16k context window is often more than enough. Of course, those with more memory can opt for a larger one. It's clearly much smarter than homogeneous quantized versions of the same size.

Downloads last month: 6

GGUF

Model size

671B params

Architecture

deepseek2

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF

Base model

deepseek-ai/DeepSeek-R1-0528

Quantized

(47)

this model