Instructions to use unsloth/DeepSeek-R1-GGUF-UD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-R1-GGUF-UD with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)

llama-cpp-python

How to use unsloth/DeepSeek-R1-GGUF-UD with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/DeepSeek-R1-GGUF-UD",
	filename="BF16/DeepSeek-R1-BF16-00001-of-00030.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use unsloth/DeepSeek-R1-GGUF-UD with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

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 unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

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 unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/DeepSeek-R1-GGUF-UD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/DeepSeek-R1-GGUF-UD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/DeepSeek-R1-GGUF-UD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

SGLang

How to use unsloth/DeepSeek-R1-GGUF-UD 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 "unsloth/DeepSeek-R1-GGUF-UD" \
    --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": "unsloth/DeepSeek-R1-GGUF-UD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "unsloth/DeepSeek-R1-GGUF-UD" \
        --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": "unsloth/DeepSeek-R1-GGUF-UD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/DeepSeek-R1-GGUF-UD with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/DeepSeek-R1-GGUF-UD 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 unsloth/DeepSeek-R1-GGUF-UD 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 unsloth/DeepSeek-R1-GGUF-UD to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use unsloth/DeepSeek-R1-GGUF-UD with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-R1-GGUF-UD with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-R1-GGUF-UD-UD-Q4_K_XL

List all available models

lemonade list

danielhanchen commited on Apr 28, 2025

Commit

683d2d9

verified ·

1 Parent(s): 46e1254

Add files using upload-large-folder tool

Browse files

Files changed (24) hide show

.gitattributes +23 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00001-of-00006.gguf +3 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00002-of-00006.gguf +3 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00003-of-00006.gguf +3 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00004-of-00006.gguf +3 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00005-of-00006.gguf +3 -0
Q3_K_S/DeepSeek-R1-Q3_K_S-00006-of-00006.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00001-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00002-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00003-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00004-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00005-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00006-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00007-of-00008.gguf +3 -0
Q4_0/DeepSeek-R1-Q4_0-00008-of-00008.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00001-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00002-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00003-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00004-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00005-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00006-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00007-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00008-of-00009.gguf +3 -0
Q4_1/DeepSeek-R1-Q4_1-00009-of-00009.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -167,3 +167,26 @@ IQ4_XS/DeepSeek-R1-IQ4_XS-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -tex
 IQ4_XS/DeepSeek-R1-IQ4_XS-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 IQ4_NL/DeepSeek-R1-IQ4_NL-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 IQ4_NL/DeepSeek-R1-IQ4_NL-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text

 IQ4_XS/DeepSeek-R1-IQ4_XS-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 IQ4_NL/DeepSeek-R1-IQ4_NL-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 IQ4_NL/DeepSeek-R1-IQ4_NL-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00009-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00008-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00006-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00007-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00005-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00002-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/DeepSeek-R1-Q3_K_S-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00001-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00004-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_1/DeepSeek-R1-Q4_1-00003-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_0/DeepSeek-R1-Q4_0-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text

Q3_K_S/DeepSeek-R1-Q3_K_S-00001-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:429c4209ebe00f102e0fa045ae736ea62afb46e89e9ff41426927866e13a9fa4
+size 49875326016

Q3_K_S/DeepSeek-R1-Q3_K_S-00002-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c526a7a109a55e5e122aa278d0ff42ce3bb9c99fa29a31ee71c53cdabaa54071
+size 49564576288

Q3_K_S/DeepSeek-R1-Q3_K_S-00003-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e99fa6e0fa1266d0a4b799334ee1ede5c5c784026e1eadb61bc5add7c1ff3859
+size 49564576288

Q3_K_S/DeepSeek-R1-Q3_K_S-00004-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa840f83d595920588367123dba5e08ea144912a0ad92356c5a3e7b0d509d607
+size 49564576288

Q3_K_S/DeepSeek-R1-Q3_K_S-00005-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9783cbfb85d726fae7de8efdb8452a73f69ede61d9a1469a243ff96665db6561
+size 49564576288

Q3_K_S/DeepSeek-R1-Q3_K_S-00006-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a08f1aa78b091e8cf2e8993ccadd03bdd4ef4aba2d50f6112f1059ca51d0bc59
+size 41272776096

Q4_0/DeepSeek-R1-Q4_0-00001-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5dcdb45c466320526e27de992d0b9a2317cc61b0abc0b0e2c5bbb925d4fd72
+size 48745381792

Q4_0/DeepSeek-R1-Q4_0-00002-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:698c29eec8a48ad7cb061dfe1f5878cd18b864a0df5ded9e445a38cb4765f21e
+size 49635606016

Q4_0/DeepSeek-R1-Q4_0-00003-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb277b3d8b2c7844a30097341c665f50f80cb915bace880b24682ade0ba2327
+size 49737716736

Q4_0/DeepSeek-R1-Q4_0-00004-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2c324981312126f3f284cace2f2476cce61fd5b31f14da1ef41cd22bcd5ff1
+size 49745085568

Q4_0/DeepSeek-R1-Q4_0-00005-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5ccd605fa9329471ba72b14a4ea6354752a888c52713b3e8424b0bfa72fdb0
+size 49635606016

Q4_0/DeepSeek-R1-Q4_0-00006-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f30328b5899ffdac3425d5b572831eb1f9b4c9cde1560dfc76df397de465675
+size 49737716736

Q4_0/DeepSeek-R1-Q4_0-00007-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45c6eb4054ff651877c53492069c90c6a5e84897bc0c42e3022b3514f7c089d5
+size 49745085568

Q4_0/DeepSeek-R1-Q4_0-00008-of-00008.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:66cf6a8aa66221e156166ba59b0b70221462c2e899927024369974e4323bd941
+size 32307565792

Q4_1/DeepSeek-R1-Q4_1-00001-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:15730a3277301efe3ebaa49ba2b60111247af0ad8d3e181bcef4a552561b3e88
+size 48140298144

Q4_1/DeepSeek-R1-Q4_1-00002-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a0309dd5ddcd8a0859ea1cd8eb7eba3e57ab04c6444c391311edb45eb7d19
+size 48055835616

Q4_1/DeepSeek-R1-Q4_1-00003-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6a417918a03fd8dfa7caae8848e7d6c7e520b070756ba49e0da55310529a8c20
+size 47935186304

Q4_1/DeepSeek-R1-Q4_1-00004-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:706ff050e53675f272d80942a4dadee34a9e729ba0dc1b18feef85e9106657e1
+size 48048466816

Q4_1/DeepSeek-R1-Q4_1-00005-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cebbef353f3968a17cf430857f5154d05fe6f4d0689cd0aabf7ff30f809da9dd
+size 48055835616

Q4_1/DeepSeek-R1-Q4_1-00006-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6e56e9ca525cf75bc1eb84fafc30ab72620526a9de598ae9051778b3b4459d
+size 47935186304

Q4_1/DeepSeek-R1-Q4_1-00007-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef52a0a5960515646265b18a4b7300d94bfc59e0fb66af38a39f1f0fb2c2a0a9
+size 48048466816

Q4_1/DeepSeek-R1-Q4_1-00008-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ed33f4f505f83941b1e2423e1ef08d35157de06045bcdfe2e20de87b749431
+size 48055835616

Q4_1/DeepSeek-R1-Q4_1-00009-of-00009.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5ec8b2a78ba9781ca7fed1d2d2df4fcc4e928863e9b3f59da9a77d3f839ecb
+size 35889222880