Instructions to use unsloth/DeepSeek-V3-0324-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-V3-0324-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-V3-0324-GGUF", 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-V3-0324-GGUF", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-V3-0324-GGUF", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/DeepSeek-V3-0324-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-V3-0324-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-V3-0324-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-V3-0324-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-V3-0324-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-V3-0324-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-V3-0324-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-V3-0324-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/DeepSeek-V3-0324-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/DeepSeek-V3-0324-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-V3-0324-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/DeepSeek-V3-0324-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-V3-0324-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-V3-0324-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-V3-0324-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-V3-0324-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/DeepSeek-V3-0324-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use unsloth/DeepSeek-V3-0324-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-V3-0324-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-V3-0324-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-V3-0324-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

danielhanchen commited on Mar 25, 2025

Commit

4a4b47e

verified ·

1 Parent(s): 0c50027

Add files using upload-large-folder tool

Browse files

Files changed (31) hide show

.gitattributes +30 -0
BF16/DeepSeek-V3-0324-BF16-00001-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00002-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00003-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00004-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00005-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00006-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00007-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00008-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00009-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00010-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00011-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00012-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00013-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00014-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00015-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00016-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00017-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00018-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00019-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00020-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00021-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00022-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00023-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00024-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00025-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00026-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00027-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00028-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00029-of-00030.gguf +3 -0
BF16/DeepSeek-V3-0324-BF16-00030-of-00030.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -96,3 +96,33 @@ UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00001-of-00005.gguf filter=lfs diff=lfs m
 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text

 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00017-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00018-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00012-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00016-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00014-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00015-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00030-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00011-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00009-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00013-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00019-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00010-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00001-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00028-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00024-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00027-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00026-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00003-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00002-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00022-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00021-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00025-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00023-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00006-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00005-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00004-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00029-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00007-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00008-of-00030.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/DeepSeek-V3-0324-BF16-00020-of-00030.gguf filter=lfs diff=lfs merge=lfs -text

BF16/DeepSeek-V3-0324-BF16-00001-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:77643061a0d0f3661709fca3125508c9e9fd21240ac2ab83e3616eb232b28f67
+size 43879928448

BF16/DeepSeek-V3-0324-BF16-00002-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc2ea755f2dd2c0f7023f34e58842accfa51d7db2a21fcafd6a958dce4a5659
+size 46036553952

BF16/DeepSeek-V3-0324-BF16-00003-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fb3bc9eb7af42b832bae430cd725fa73d5f9ef890dfe0b0044d748ad541fb8
+size 46036553952

BF16/DeepSeek-V3-0324-BF16-00004-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:94c9a7db24f83cc811cfa11fc57c509c32d46abc32764b7683595815305c908f
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00005-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:308465e92d338319a8ccd5e381ccda1e46e139affe7ce47738b4cc3a36ced390
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00006-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:803502b94968103f5a7444bde5ebbbef7a46f1007f132dbcf8b91102a49d491f
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00007-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef97e2b0757df84d146aac606fd19c62b91edfa0cada3e04e525cc23859962e
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00008-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e7cf73a1444f768094d6dff982a2bb1a2688b0aaef26eec632b3c8ffeaa401
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00009-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:881f6f22c441d3560c56970df3eb7caa51b485602f36c944e22ff97a9a7a187c
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00010-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e590013b11469e8f872a7aaaf63ea1f759a6a813ed15ee75aab2a6addee6142
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00011-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:96c0650fe4082134bf10bca2ed952e32388ca97f2e0df31d1805aaea9ba20554
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00012-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:10a56019bc500a15bee89682e499b34842aa8d717fd299e0b588bf292cad03bc
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00013-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:70f45f52112e523aca6c411e84e35398fe6c88db97497a1da3158276f8de2916
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00014-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3df6d9a76221794f01b29a52e048ae8afd66f5d69ad105e50782c974f5e28e1
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00015-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:eebd7c59e508cf7dab3dc93b4ad026c33c3ed395e5c5c292de36e732fe1a0eb1
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00016-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7f212b772a7bbafd24c39e9c56ccd55dedb4491a1a60202f347d458d5b4f242d
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00017-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a58e3fb1f56da7431e3429e792831afdb7fe13c95d6bb2b89226ab4e7d796acb
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00018-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9697b7c7dcb2d6e66ee4b7eedad0e1b762bac10f457b4a4f32caf3cf67eeb053
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00019-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:254cdc2284c176923e5649aaf85347733d0598bc674a53443b94298c30bc3594
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00020-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfaac4b906c8804dffbb3ec635c4f555e6fdd7ab13b74586a5fbad8c118d34f
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00021-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:06d82e1f2daef4071d1012eac212f34ec6d64ed293d81603f9b5c1a39f9c5deb
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00022-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6edc0a0759b5bc231ddff1a55b60f1e2eacc32da5326eef203950264047843
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00023-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4849dd30d855efe56c5306ffe15687746f155759475ea579398064fad9b9bc5
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00024-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa806cf007082fe849c34513fa8a2c1b5637d379a9dc1b3d40f1ca79cc0de12
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00025-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b283000b74ae4a2ce0d98e373ada67dc8f11e985f8cc2b0112025508050f7ac
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00026-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:25ebe7023d162d7a708c3b5558aeeef9b728e09f38d7bc2d9ff79caa2b7ac7e8
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00027-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a2e1573fde22616a8b607e3e4e85cbc2d72d66a3e6a3ab8d6cbbcb42c54cc1
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00028-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:96dfe10115086c3a62b3c46f9f1c95c5d9d65e943e2546be8ec2bab9d35d45f9
+size 46036553984

BF16/DeepSeek-V3-0324-BF16-00029-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:434ccdb4bb8eaea3a633a2d22bab6200e9b8794ba061c7f17f4bc6723b777306
+size 47889912128

BF16/DeepSeek-V3-0324-BF16-00030-of-00030.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:35c2ed6472dd394eb6a8ec334b9f40af084281d9d43eddc6dcbe8444110bc585
+size 7516250400