Subscribe and Support

This is Nanbeige/Nanbeige4.1-3B quantized with llm-compressor to W8A8 (FP8) . The model is compatible with vLLM (tested: v0.15.1). Tested with an L4 (Google Colab).

Developed by: The Kaitchup

Downloads last month: 23

Safetensors

Model size

4B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

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

Model tree for kaitchup/Nanbeige4.1-3B-FP8-Dynamic

Base model

Nanbeige/Nanbeige4-3B-Base

Finetuned

Nanbeige/Nanbeige4.1-3B

Quantized

(40)

this model

Collection including kaitchup/Nanbeige4.1-3B-FP8-Dynamic

Quantized Nanbeige4.1-3B

Collection

Verified models. Compatible with vLLM v0.15.1. • 5 items • Updated 1 day ago