Instructions to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant", dtype="auto")

llama-cpp-python

How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant",
	filename="DeepSeek-R1-Distill-Llama-8B-NexaQuant.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
# Run inference directly in the terminal:
llama-cli -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
# Run inference directly in the terminal:
llama-cli -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

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 NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
# Run inference directly in the terminal:
./llama-cli -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

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 NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

Use Docker

docker model run hf.co/NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

LM Studio
Jan
Ollama
How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with Ollama:
```
ollama run hf.co/NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
```

Unsloth Studio new

How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant 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 NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant 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 NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant to start chatting

Docker Model Runner
How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with Docker Model Runner:
```
docker model run hf.co/NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant
```

Lemonade

How to use NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Llama-8B-NexaQuant-{{QUANT_TAG}}

List all available models

lemonade list

Update README.md

by yli-nexa4ai - opened Feb 12, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+58

-1

Files changed (1) hide show

README.md +58 -1

README.md CHANGED Viewed

@@ -66,4 +66,61 @@ Get the latest version from the [official website](https://lmstudio.ai/).
 1. In LM Studio's top panel, search for and select `NexaAIDev/DeepSeek-R1-Distill-Llama-8B-NexaQuant`.
 2. Click `Download` (if not already downloaded) and wait for the model to load.
 3. Once loaded, go to the chat window and start a conversation.
----

 1. In LM Studio's top panel, search for and select `NexaAIDev/DeepSeek-R1-Distill-Llama-8B-NexaQuant`.
 2. Click `Download` (if not already downloaded) and wait for the model to load.
 3. Once loaded, go to the chat window and start a conversation.
+---
+## Example
+On the left, we have an example of what LMStudio Q4_K_M responded. On the right is our NexaQuant version.
+Prompt: A Common Investment Banking BrainTeaser Question
+There is a 6x8 rectangular chocolate bar made up of small 1x1 bits. We want to break it into the 48 bits. We can break one piece of chocolate horizontally or vertically, but cannot break two pieces together! What is the minimum number of breaks required?
+Right Answer: 47
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66abfd6f65beb23afa427d8a/ZS9e66t7OhBIno4eQ3OaX.png" width="80%" alt="Example" />
+</div>
+## Benchmarks
+NexaQuant on Reasoning Benchmarks Compared to BF16 and LMStudio's Q4_K_M
+**8B:**
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66abfd6f65beb23afa427d8a/4SSDIqxikgaDbx8V-Q6bf.png" width="80%" alt="Example" />
+</div>
+The general capacity has also greatly improved:
+**8B:**
+| Benchmark                  | Full 16-bit | llama.cpp (4-bit) | NexaQuant (4-bit)|
+|----------------------------|------------|-------------------|-------------------|
+| **HellaSwag**              | 57.07      | 52.12             | 54.56             |
+| **MMLU**                   | 55.59      | 52.82             | 54.94             |
+| **Humanities**             | 50.48      | 44.74             | 50.24             |
+| **Social Sciences**        | 65.32      | 65.62             | 64.74             |
+| **STEM**                   | 47.73      | 52.50             | 46.75             |
+| **ARC Easy**               | 74.49      | 69.32             | 71.72             |
+| **MathQA**                 | 35.34      | 30.00             | 32.46             |
+| **PIQA**                   | 78.56      | 76.09             | 77.68             |
+| **IFEval - Inst - Loose**  | 44.24      | 44.95             | 42.45             |
+| **IFEval - Inst - Strict** | 42.57      | 44.95             | 40.05             |
+| **IFEval - Prom - Loose**  | 30.31      | 25.74             | 28.47             |
+| **IFEval - Prom - Strict** | 27.91      | 25.74             | 25.51             |
+## What's next
+1. Inference Nexa Quantized Deepseek-R1 distilled model on NPU.
+2. This model is designed for complex problem-solving, which is why it has a longer thinking process. We understand this can be an issue in some cases, and we're actively working on improvements.
+### Follow us
+If you liked our work, feel free to ⭐Star [Nexa's GitHub Repo](https://github.com/NexaAI/nexa-sdk).
+Interested in running DeepSeek R1 on your own devices with optimized CPU, GPU, and NPU acceleration or compressing your finetuned DeepSeek-Distill-R1? [Let’s chat!](https://nexa.ai/book-a-call)
+[Blogs](https://nexa.ai/blogs/quantized-deepseek-r1-on-device) | [Discord](https://discord.gg/nexa-ai) | [X(Twitter)](https://x.com/nexa_ai)