Description

NVFP4 Quantization of Qwen/Qwen3-Coder-30B-A3B-Instruct using TensorRT-Model-Optimizer. KV Cache quantized to FP8 for compatibility with inference backends.

Downloads last month
100
Safetensors
Model size
16B params
Tensor type
BF16
F8_E4M3
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for rahtml/Qwen3-Coder-30B-A3B-Instruct-NVFP4

Quantized
(113)
this model