Instructions to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/DeepSeek-R1-Distill-Llama-70B-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 unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF: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-Distill-Llama-70B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF: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-Distill-Llama-70B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL

Llama new
LM Studio
Jan

vLLM

How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF"
# 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-Distill-Llama-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF 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-Distill-Llama-70B-GGUF" \
    --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-Distill-Llama-70B-GGUF",
		"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-Distill-Llama-70B-GGUF" \
        --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-Distill-Llama-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Llama-70B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

danielhanchen commited on May 10, 2025

Commit

3f97ef3

verified ·

1 Parent(s): 890e183

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

.gitattributes +5 -0
DeepSeek-R1-Distill-Llama-70B-IQ4_NL.gguf +3 -0
DeepSeek-R1-Distill-Llama-70B-IQ4_XS.gguf +3 -0
DeepSeek-R1-Distill-Llama-70B-Q2_K_L.gguf +2 -2
DeepSeek-R1-Distill-Llama-70B-Q3_K_S.gguf +3 -0
DeepSeek-R1-Distill-Llama-70B-Q4_0.gguf +3 -0
DeepSeek-R1-Distill-Llama-70B-Q4_1.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -55,3 +55,8 @@ DeepSeek-R1-Distill-Llama-70B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -tex
 DeepSeek-R1-Distill-Llama-70B-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 Q6_K/DeepSeek-R1-Distill-Llama-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
 Q6_K/DeepSeek-R1-Distill-Llama-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text

 DeepSeek-R1-Distill-Llama-70B-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 Q6_K/DeepSeek-R1-Distill-Llama-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
 Q6_K/DeepSeek-R1-Distill-Llama-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-70B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-70B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-70B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-70B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-70B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text

DeepSeek-R1-Distill-Llama-70B-IQ4_NL.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cec649b31da121fb9448249e2184944e7bc84fe62451803e99ab11a102776c22
+size 40053621408

DeepSeek-R1-Distill-Llama-70B-IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:58b57114dabd6efb1ac9c81db5571099e3a35fea32638fe226da4c3e11b7c83e
+size 37935497888

DeepSeek-R1-Distill-Llama-70B-Q2_K_L.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec176fc627bcf936bad4aa52f7e1a1eac3b3a63e6c6de3f0fd83b79b955b015
-size 26621362624

 version https://git-lfs.github.com/spec/v1
+oid sha256:ad0706ae66013d80a9d8c7f3f65fd76887456764e053c4efe6b2f17b2268c1c8
+size 26621362848

DeepSeek-R1-Distill-Llama-70B-Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:79380de921a957d6e42552b048b53c6139ff567ad1f24b17cc5ef7a535d26569
+size 30912053920

DeepSeek-R1-Distill-Llama-70B-Q4_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:97de86b28911d3b4c53e2e0ef27b5ad877c2a5a54ba97ec09a30e16757d1885b
+size 40116535968

DeepSeek-R1-Distill-Llama-70B-Q4_1.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ba210740e740c6908daa6f7ab2669c60bb52f7170f9ffbb0879320cbc4cdda3b
+size 44313592480