Instructions to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF", dtype="auto")

MLX

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir DeepSeek-R1-Distill-Qwen-7B-GGUF tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF

llama-cpp-python

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF",
	filename="DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

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 tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

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 tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with Ollama:
```
ollama run hf.co/tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF 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 tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF 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 tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K
```

Lemonade

How to use tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q2_K

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-7B-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Mar 9, 2025

Commit

ec1cbf9

verified ·

1 Parent(s): 8babf0f

Upload folder using huggingface_hub

Browse files

Files changed (13) hide show

DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf +2 -2
DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf +2 -2
README.md +4 -11

DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc014397426ea004c0cff51a5473a10c11bd8ab7af6fc855c4a775eb699dc52
-size 3015940320

 version https://git-lfs.github.com/spec/v1
+oid sha256:0ceea38791156394d037e5e8400252092a7359c76c4cd46857edffdd0f17bca9
+size 3015940128

DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692ca9240525bfeb7ebf66d071d8715eb62f23fa6b55199a87bb6dbe1b750e35
-size 4088459488

 version https://git-lfs.github.com/spec/v1
+oid sha256:343e0e12ba576018ab57d0276e81e7c14feec3f39560ae1fc6cd4016976320ae
+size 4088459296

DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c1ae461ddc5478ea26166a0889772456c7cffdd6ed5202b3010fa8cbe5f7d9
-size 3808391392

 version https://git-lfs.github.com/spec/v1
+oid sha256:8aeb2ba5189021102167d6e56bbb646fdf5a0810ae70e49e13b7e8f0cc3fe3d4
+size 3808391200

DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2951e3e8b132857411e480cd604558cbdd4b3c6577b7bca037d1b8f754368bf5
-size 3492368608

 version https://git-lfs.github.com/spec/v1
+oid sha256:63f8926259ae127e2a1219ad05e42761b4db3c88b0d920d5ae87a458c1806e78
+size 3492368416

DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41bbfb92462047805204fb0dc55c4942ae13239118d2636465805cca0506f6c9
-size 4431390944

 version https://git-lfs.github.com/spec/v1
+oid sha256:c66c9d952699ca34c2d91cc69904128103ac2ee9a979c3e5811f4a4855772648
+size 4431390752

DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bc44d49590a4224184677735b8236887e87b0ecde90bae44d0179b9dfd7909
-size 4683073760

 version https://git-lfs.github.com/spec/v1
+oid sha256:d726cc98c5fba023d6f534698caf6cc8f9870d45be763616ce7521c32f7dfc51
+size 4683073568

DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad669fd29e49906bc146da8b7babac6d9d327c96dccb133616484b9584f6356f
-size 4457769184

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd0f51f394684e097335a78bbd8df05d5e1b2affac135484db5ce3132cac9c6c
+size 4457768992

DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7790f49ee3d2f6cc74223c2523f3aafb74c3df2f2e76eb47fa756534edd2306f
-size 5315176672

 version https://git-lfs.github.com/spec/v1
+oid sha256:c354665cc9d0ab42f81e214baf08a3563ebb8422aa3328b7a9276acbbd2638fb
+size 5315176480

DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d979a01c60e76bfc97039f65aa5c3e7f231af8514a73e5f9d052057f6cf44b
-size 5444831456

 version https://git-lfs.github.com/spec/v1
+oid sha256:d0f1c7f8f609cab089861af6b913783c721afbc9345cf55d2b080c326182c989
+size 5444831264

DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94d118fe4ef65c1f71570c72e6c911b89dee55b7374e196b24332198c61b0c7
-size 5315176672

 version https://git-lfs.github.com/spec/v1
+oid sha256:ff974c5add06f1dfa19d1a16b710acd01a1dced9613b614a754e6a4d74c5fe77
+size 5315176480

DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33135cb1fbcfe8462034a0e4ab5abf5f1ee1e2a99e1b0ed998a0766a27e5c33d
-size 6254199008

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5cc349c97c74d0c36b91e506bf30c7133474c71322f584f702c9140befa3ad5
+size 6254198816

DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a92d5a118bd0575d88b27646f00e1a9448f385f0b34921aba3723d99940c97a
-size 8098525408

 version https://git-lfs.github.com/spec/v1
+oid sha256:541e5c16400bd1e7feb49b7d4ba192a61bc26dab567d1f81581079fadc8cc3b9
+size 8098525216

README.md CHANGED Viewed

@@ -1,17 +1,10 @@
 ---
-base_model: unsloth/DeepSeek-R1-Distill-Qwen-7B
-language:
-- en
-license: apache-2.0
 library_name: transformers
 tags:
-- deepseek
-- qwen
-- qwen2
-- unsloth
-- transformers
 - TensorBlock
 - GGUF
 ---
 <div style="width: auto; margin-left: auto; margin-right: auto">
@@ -25,9 +18,9 @@ tags:
     </div>
 </div>
-## unsloth/DeepSeek-R1-Distill-Qwen-7B - GGUF
-This repo contains GGUF format model files for [unsloth/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B).
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).

 ---
 library_name: transformers
 tags:
+- mlx
 - TensorBlock
 - GGUF
+base_model: mlx-community/DeepSeek-R1-Distill-Qwen-7B
 ---
 <div style="width: auto; margin-left: auto; margin-right: auto">
     </div>
 </div>
+## mlx-community/DeepSeek-R1-Distill-Qwen-7B - GGUF
+This repo contains GGUF format model files for [mlx-community/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-7B).
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).