Atlas

Models

← All models

Kimi-VL-A3B-Instruct

Moonshot AI · 2025-04-10 · 16.4B parameters

Kimi-VL-A3B-Instruct is Moonshot AI's non-thinking instruction-tuned Kimi-VL checkpoint for text, image, and video understanding, separately distributed from the Kimi-VL-A3B-Thinking weights. It combines a native-resolution MoonViT encoder, an MLP projector, and a Moonlight MoE language decoder; Moonshot reports rounded 16B-total and 2.8B-decoder-plus-0.4B-vision activated figures, while the released BF16 tensors contain exactly 16,407,657,776 parameters and the configuration supports 131,072 positions.

Benchmark scores

BenchmarkScore
AI2D (OpenVLM)84.5
Capability121.0
HallusionBench (OpenVLM)48.4
MATH-Vision21.4
MathVista (OpenVLM)66.0
MM-Vet (OpenVLM)66.1
MMMU Validation (OpenVLM)57.8
MMStar (OpenVLM)62.0
OSWorld8.2
Loading Atlas data…