EXL3 quantization of Jan-v3-4B-base-instruct, 8 bits per weight, including output layers.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for isogen/Jan-v3-4B-base-instruct-exl3-8bpw-h8
Base model
Qwen/Qwen3-4B-Instruct-2507 Finetuned
janhq/Jan-v3-4B-base-instruct