This is Qwen/Qwen3-VL-2B-Instruct quantized with AutoRound in NVFP4 (llm-compressor format). The model has been created, tested, and evaluated by The Kaitchup. The model is NOT compatible with vLLM (as of v0.11).

Developed by: The Kaitchup
License: Apache 2.0 license

How to Support My Work

Subscribe to The Kaitchup. This helps me a lot to continue quantizing and evaluating models for free. Or you prefer to give some GPU hours, "buy me a coffee"

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

F32

BF16

F8_E4M3

Inference Providers NEW

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

Model tree for kaitchup/Qwen3-VL-2B-Instruct-NVFP4

Base model

Qwen/Qwen3-VL-2B-Instruct

Quantized

(36)

this model

Collection including kaitchup/Qwen3-VL-2B-Instruct-NVFP4

Quantized Qwen3-VL

Collection

4 items • Updated Nov 5