User:<image>Describe the image.

Answer: In this captivating digital painting, an astronaut is comfortably seated on the surface of the moon, with their feet propped up on a green cooler. The astronaut, clad in a pristine white spacesuit, has a relaxed posture, suggesting they are enjoying a leisurely moment away from the hustle and bustle of space exploration.

The backdrop to this tranquil scene is a breathtaking view of Earth, which is visible in the distance. The planet's blue oceans contrast beautifully with its brown landmasses, while its white clouds add depth to the atmosphere. The moon itself forms a stark, cratered landscape that serves as an excellent contrast to the vibrant colors of Earth.

The astronaut's gaze is directed towards the Earth, indicating their fascination with our home planet. Their relaxed demeanor and the presence of the cooler suggest they might be taking a break from their spacewalk or perhaps enjoying a well-deserved moment on the lunar surface. The painting beautifully captures this serene moment in space exploration, highlighting both the astronaut's peaceful solitude and the awe-inspiring beauty of Earth.

Model Files

Component	File	Precision
LLM	`smolvlm2-2.2b-instruct_w8a8_rk3588.rkllm`	W8A8
Vision Encoder	`smolvlm2-2.2b_vision_fp16_rk3588.rknn`	FP16

Hardware Requirements

Rockchip RK3588 / RK3588S
RKNPU2 driver
Tested on:
- Rock 5C
- Ubuntu 22.04 / 24.04 (Joshua Riek)

Runtime Requirements

RKLLM runtime
RKNN runtime (rknpu2)
OpenCV (for image preprocessing)

Model performance benchmark (FPS)

All models, with C++ examples, can be found on the Q-engineering GitHub.

All LLM models are quantized to w8a8, while the VLM vision encoders use fp16.

model	RAM (GB)¹	llm cold sec²	llm warm sec³	vlm cold sec²	vlm warm sec³	Resolution	Tokens/s
Qwen3-2B	3.1	21.9	2.6	10.0	0.9	448 x 448	11.5
Qwen3-4B	8.7	49.6	5.6	10.6	1.1	448 x 448	5.7
Qwen2.5-3B	4.8	48.3	4.0	17.9	1.8	392 x 392	7.0
Qwen2-7B	8.7	86.6	34.5	37.1	20.7	392 x 392	3.7
Qwen2-2.2B	3.3	29.1	2.5	17.1	1.7	392 x 392	12.5
InternVL3-1B	1.3	6.8	1.1	7.8	0.75	448 x 448	30
SmolVLM2-2.2B	3.4	21.2	2.6	10.5	0.9	384 x 384	11
SmolVLM2-500M	0.8	4.8	0.7	2.5	0.25	384 x 384	31
SmolVLM2-256M	0.5	1.1	0.4	2.5	0.25	384 x 384	54

¹ The total used memory; LLM plus the VLM.
² When an llm/vlm model is loaded for the first time from your disk to RAM or NPU, it is called a cold start.
The duration depends on your OS, I/O transfer rate, and memory mapping.
³ Subsequent loading (warm start) takes advantage of the already mapped data in RAM. Mostly, only a few pointers need to be restored.

Example Usage

see: https://github.com/Qengineering/SmolVLM2-2B-NPU

Notes

This is not a Transformers-compatible model
This repository provides precompiled NPU binaries
CPU fallback is not supported

Qengineering/smolvlm2-2.2b-rk3588

SmolVLM2-2.2B for RK3588 NPU