Skyfall-31B-v4.2-int8
This repository contains a weight-only INT8 quantized version of TheDrummer/Skyfall-31B-v4.2.
Notes:
- Quantized on Kaggle using CPU + RAM disk (
/dev/shm) - Quantization backend: Optimum Quanto
- Intended as an uploaded INT8 artifact; TPU runtime compatibility depends on the serving stack
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for vekotov/Skyfall-31B-v4.2-int8
Base model
mistralai/Mistral-Small-3.1-24B-Base-2503 Finetuned
mistralai/Magistral-Small-2509 Finetuned
TheDrummer/Skyfall-31B-v4.2