Ministral 3B Instruct (Abliterated) - GGUF

Quantized to Q4_K_M by NovachronoAI.

Usage (Termux / Android)

./llama-cli -m ministral-3b-abliterated-Q4_K_M.gguf -p "User: Hello\nAssistant:" -n 400 -t 4

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Base model

Quantized

Quantized

Quantized

(1)

this model