Rockchip RK3576 / Qwen3 0.6B
Can a Rockchip RK3576 run Qwen3 0.6B?
Yes, at a comfortable chat speed. Measured generation speed: 17.17–24.85 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.
| Board | Quant | Runtime | Gen tok/s | Prompt tok/s | TTFT ms | Source |
|---|---|---|---|---|---|---|
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | w4a16 | RKLLM v1.3.1 | 24.85 | – | 468.61 | source ↗ commit 2026-09-29 |
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | w4a16_g128 | RKLLM v1.3.1 | 23.48 | – | 506.41 | source ↗ commit 2026-09-29 |
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | w8a8 | RKLLM v1.3.1 | 17.17 | – | 461.54 | source ↗ commit 2026-09-29 |
Qwen3 0.6B on other boards
- Rockchip RK3588 32.91 tok/s best
- M5Stack LLM8850 12.88 tok/s best
- M5Stack Module LLM 10.28 tok/s best
Buy a Rockchip RK3576
- Radxa ROCK 4D 8GB: $106 listed price, source ↗ (2026-10-17) Check price on Amazon
Ran Qwen3 0.6B on a Rockchip RK3576? Submit your numbers →