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 Desktop
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

Atomic Chat

mmbela commited on Jun 5, 2025

Commit

54260ab

verified ·

1 Parent(s): b26cd83

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -6,4 +6,4 @@ base_model:
 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 "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.


6	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.
7
8
9	+ 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.