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

Libraries

How to use tensorblock/NuminaMath-7B-TIR-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/NuminaMath-7B-TIR-GGUF",
	filename="NuminaMath-7B-TIR-Q2_K.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 tensorblock/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/NuminaMath-7B-TIR-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/NuminaMath-7B-TIR-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": "tensorblock/NuminaMath-7B-TIR-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K

Ollama
How to use tensorblock/NuminaMath-7B-TIR-GGUF with Ollama:
```
ollama run hf.co/tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-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/NuminaMath-7B-TIR-GGUF to start chatting

Docker Model Runner
How to use tensorblock/NuminaMath-7B-TIR-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K
```

Lemonade

How to use tensorblock/NuminaMath-7B-TIR-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/NuminaMath-7B-TIR-GGUF:Q2_K

Run and chat with the model

lemonade run user.NuminaMath-7B-TIR-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:25d3000bc4d535e972d648233e5dee1c689eda3c6bed6d44e6d2279260b53740
-size 3746273440

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a371169d707d2c14f32de04a6e0b9a185f6d1e6c4a8bee2e296490c1c76eacbd
-size 3461191840

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be89a2dccb791758403044f548f67cd1cb61c74b4c98da4e5e46fa2cf9af38ad
-size 3138017440

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d2b3d8b44f769df43dc9a386ccf127f2ab1dd972d645d4df2cd69bb607d0ef3
-size 4000061600

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e67c6537b0893606a31b8885ef757a8fa1c1855c3600e882e655ba769d292d1d
-size 4223359136

tensorblock
/

NuminaMath-7B-TIR-GGUF

Remove .gguf files (keep Q2_K.gguf)