Instructions to use tensorblock/KULLM3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/KULLM3-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/KULLM3-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/KULLM3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/KULLM3-GGUF",
	filename="KULLM3-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/KULLM3-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/KULLM3-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/KULLM3-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/KULLM3-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/KULLM3-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/KULLM3-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/KULLM3-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/KULLM3-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/KULLM3-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/KULLM3-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/KULLM3-GGUF with Ollama:
```
ollama run hf.co/tensorblock/KULLM3-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/KULLM3-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/KULLM3-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/KULLM3-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/KULLM3-GGUF to start chatting

Docker Model Runner
How to use tensorblock/KULLM3-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/KULLM3-GGUF:Q2_K
```

Lemonade

How to use tensorblock/KULLM3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/KULLM3-GGUF:Q2_K

Run and chat with the model

lemonade run user.KULLM3-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

bc26630

verified ·

1 Parent(s): a845c86

Keep Q2_K/Q3_K_M gguf only

Browse files

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65793fcf28d62e14384b165f0b8eaf401a63da4f4a3b75c559801eff53512d87
-size 5650751712

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f6484d04c63055fb7f72d047fa7c98c418c6c067bccbe22e97d7d907098c4e0
-size 4664565984

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed440613c6814bb74d8724c4d7f95dc5f4836b8075cfe4e252c54d05208e74c2
-size 6072385760

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c094541ee3f3d83f543b4ae6f1f420e3ab50d94d61ece85fd7d6a883662897ca
-size 6461669600

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:38432f7c2c6f855f106d62b1af77a53011a087631fa60458f72c3f94f74ff8a2
-size 6118523104