Qwen3-VL-8B-Instruct

Original model repository: Qwen/Qwen3-VL-8B-Instruct

Model Introduction

Qwen3-VL-8B-Instruct is an instruction-tuned Vision-Language Model (VLM) for understanding images, videos, and text. It combines a vision encoder with a dense autoregressive language model. The model supports visual question answering, multilingual OCR, document understanding, visual grounding, spatial reasoning, video understanding, visual coding, and visual-agent tasks.

Deployment Metrics

Model Parameters

Metric	Value
Total model parameters	8.767B
Vision model (ViT) parameters	576.4M
Language model (LM) parameters	8.191B

Parameter counts are calculated from the tensors stored in the upstream checkpoint.

Performance Metrics

Chips	Data Type	ViT Image Size	Sequence Length (tokens)	Maximum Context Length (tokens)	BPU Cores (ViT / Prefill / Decode)	ViT Latency (ms)	TTFT (ms)	Prefill TPS (token/s)	Decode TPS (token/s)	BPU Memory (GB)	CPU Memory (GB)
Matrix6P	W8A8	448 × 448	512	1024	4 / 4 / 4	28.593	193.200	3,211.139	19.840	9.4	2.5
S6P	W8A8	448 × 448	512	1024	4 / 4 / 4	25.396	164.228	3,807.482	20.613	9.6	2.5
S6P	W4A8	448 × 448	512	1024	4 / 4 / 4	25.111	159.716	3,928.261	31.789	6.4	2.5

Note: TTFT includes preprocessing and ViT latency. Memory values represent the peak memory usage measured during the specified performance test.