Can a Rockchip RK3576 run Qwen3.5 0.8B?
Yes, at a comfortable chat speed. Measured generation speed: 13.18–18.79 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 | Size | Runtime | Gen tok/s | Source |
|---|---|---|---|---|
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | 800M | RKLLM v1.3.1 | 18.79 | source ↗ commit 2026-09-29 |
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | 800M | RKLLM v1.3.1 | 17.88 | source ↗ commit 2026-09-29 |
| Rockchip RK3576 Rockchip RK3576 (vendor reference board) | 800M | RKLLM v1.3.1 | 13.18 | source ↗ commit 2026-09-29 |
Qwen3.5 0.8B on other boards
- Rockchip RK3588 27.05 tok/s best
Buy a Rockchip RK3576
- Radxa ROCK 4D 8GB$106listed price · price source ↗ (2026-10-17)Check price on Amazon
Ran Qwen3.5 0.8B on a Rockchip RK3576? Submit your numbers →