Instructions to use fizzacles/Sapphira-L3.3-XL-100b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fizzacles/Sapphira-L3.3-XL-100b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fizzacles/Sapphira-L3.3-XL-100b",
	filename="Sapphira-L3.3-XL-100b_BF16.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 fizzacles/Sapphira-L3.3-XL-100b 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 fizzacles/Sapphira-L3.3-XL-100b:BF16
# Run inference directly in the terminal:
llama cli -hf fizzacles/Sapphira-L3.3-XL-100b:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fizzacles/Sapphira-L3.3-XL-100b:BF16
# Run inference directly in the terminal:
llama cli -hf fizzacles/Sapphira-L3.3-XL-100b:BF16

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 fizzacles/Sapphira-L3.3-XL-100b:BF16
# Run inference directly in the terminal:
./llama-cli -hf fizzacles/Sapphira-L3.3-XL-100b:BF16

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 fizzacles/Sapphira-L3.3-XL-100b:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fizzacles/Sapphira-L3.3-XL-100b:BF16

Use Docker

docker model run hf.co/fizzacles/Sapphira-L3.3-XL-100b:BF16

LM Studio
Jan
Ollama
How to use fizzacles/Sapphira-L3.3-XL-100b with Ollama:
```
ollama run hf.co/fizzacles/Sapphira-L3.3-XL-100b:BF16
```

Unsloth Studio

How to use fizzacles/Sapphira-L3.3-XL-100b 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 fizzacles/Sapphira-L3.3-XL-100b 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 fizzacles/Sapphira-L3.3-XL-100b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fizzacles/Sapphira-L3.3-XL-100b to start chatting

Atomic Chat new
Docker Model Runner
How to use fizzacles/Sapphira-L3.3-XL-100b with Docker Model Runner:
```
docker model run hf.co/fizzacles/Sapphira-L3.3-XL-100b:BF16
```

Lemonade

How to use fizzacles/Sapphira-L3.3-XL-100b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fizzacles/Sapphira-L3.3-XL-100b:BF16

Run and chat with the model

lemonade run user.Sapphira-L3.3-XL-100b-BF16

List all available models

lemonade list

As per requested, Sapphira L3.3 70b merged with itself into a 101b parameter model.

Suggested samplers:

temp 1.1
topK 200
topP 1
minP 0.02
no rep. penalties

Downloads last month: 66

GGUF

Model size

101B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fizzacles/Sapphira-L3.3-XL-100b

Base model

BruhzWater/Sapphira-L3.3-70b-0.2

Quantized

(4)

this model