flan-t5-xxl-encoder-only-GGUF

Instructions to use InsecureErasure/flan-t5-xxl-encoder-only-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InsecureErasure/flan-t5-xxl-encoder-only-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="InsecureErasure/flan-t5-xxl-encoder-only-GGUF",
	filename="flan-t5-xxl-encoder-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use InsecureErasure/flan-t5-xxl-encoder-only-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 InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

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 InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

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 InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

Use Docker

docker model run hf.co/InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use InsecureErasure/flan-t5-xxl-encoder-only-GGUF with Ollama:
```
ollama run hf.co/InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
```

Unsloth Studio

How to use InsecureErasure/flan-t5-xxl-encoder-only-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 InsecureErasure/flan-t5-xxl-encoder-only-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 InsecureErasure/flan-t5-xxl-encoder-only-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for InsecureErasure/flan-t5-xxl-encoder-only-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use InsecureErasure/flan-t5-xxl-encoder-only-GGUF with Docker Model Runner:
```
docker model run hf.co/InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M
```

Lemonade

How to use InsecureErasure/flan-t5-xxl-encoder-only-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull InsecureErasure/flan-t5-xxl-encoder-only-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.flan-t5-xxl-encoder-only-GGUF-Q4_K_M

List all available models

lemonade list

InsecureErasure/flan-t5-xxl-encoder-only-GGUF

Quantized GGUF version of Google FLAN T5-XXL (encoder only)

This repo contains additional GGUF quantizations of Google's FLAN-T5 XXL (encoder only) not available in silveroxides/flan-t5-xxl-encoder-only-GGUF, produced using llama.cpp.

These are aimed at users with limited hardware — requiring less memory and storage than higher quantization formats. Other repositories on HF include the decoder layers, resulting in a much bigger file. If you're using this for generating embeddings for Chroma or FLUX models (as I am), you only need the encoder layers.

Big kudos to silveroxides.