Rockchip RK3576 / Qwen2 0.5B

Can a Rockchip RK3576 run Qwen2 0.5B?

Yes, at a comfortable chat speed. Measured generation speed: 21.73–32.56 tok/s across 3 public runs.

Rule of thumb: 10+ tok/s feels like a chat; 4–10 is usable for assistants and automations; under 4 is batch-job territory. Speeds depend on quantization, runtime, context length and cooling. Check each source.

BoardQuantRuntimeGen tok/sPrompt tok/sTTFT msSource
Rockchip RK3576
Rockchip RK3576 (vendor reference board)
w4a16RKLLM v1.3.132.56–342.37source ↗
commit 2026-09-29
Rockchip RK3576
Rockchip RK3576 (vendor reference board)
w4a16_g128RKLLM v1.3.130.33–361.78source ↗
commit 2026-09-29
Rockchip RK3576
Rockchip RK3576 (vendor reference board)
w8a8RKLLM v1.3.121.73–344.27source ↗
commit 2026-09-29

Qwen2 0.5B on other boards

Buy a Rockchip RK3576

Ran Qwen2 0.5B on a Rockchip RK3576? Submit your numbers →

Get the monthly board report

New boards, new runtimes, new numbers. One email a month, no hype.