Products · Seeed Studio · Board
Seeed Studio reComputer RK3588-30
- Chip
- Rockchip RK3588
- Unified memory
- 8 or 16 GB
- Launch price
- $279–$349
- Released
- 2026
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| Rockchip RK3588 | 8.0 GB | 6.4 GB | 34 GB/s | 155 of 622 | $279 |
| Rockchip RK3588 | 16.0 GB | 13.6 GB | 34 GB/s | 184 of 622 | $349 |
Specifications 8.0 GB configuration
| Maker | Seeed Studio |
|---|---|
| Type | Board |
| Chip | Rockchip RK3588 / RK3588S (8 GB) |
| Unified memory | 8.0 GB |
| Usable for AI models | 6.4 GB |
| Memory bandwidth | 34 GB/s |
| FP16 compute | 0.2 TFLOPS |
| Notes | RK3588 AI box with LPDDR5, a fan and Armbian preinstalled; a PCIe slot takes an add-on accelerator. Up to 32 GB to order. |
| Product page | www.seeedstudio.com (opens in a new tab) |
Best LLMs for the Seeed Studio reComputer RK3588-30 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q4_K_M | 6.2 GB | 24.4 tok/s | Runs welltight fit |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q4_K_M | 4.3 GB | 15.0 tok/s | Runs well |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q3_K_M | 6.0 GB | 4.8 tok/s | Slowtight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q3_K_M | 6.3 GB | 4.6 tok/s | Slowtight fit |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q5_K_M | 4.0 GB | 40.8 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q3_K_M | 4.6 GB | 10.7 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q3_K_M | 6.1 GB | 4.6 tok/s | Slowtight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q3_K_M | 6.1 GB | 4.6 tok/s | Slowtight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q3_K_M | 6.1 GB | 4.6 tok/s | Slowtight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q3_K_M | 5.8 GB | 5.0 tok/s | Slowtight fit |
Best Image models for the Seeed Studio reComputer RK3588-30 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 5.7 GB | 17.5 min | Very slowtight fit · encoder unloaded after use |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 6.2 GB | 2.3 min | Very slowtight fit · encoder unloaded after use |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 6.1 GB | 7.7 min | Very slowtight fit · encoder unloaded after use |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | Q4 GGUF | 5.4 GB | 43.1 min | Very slowencoder unloaded after use |
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 4.2 GB | 20 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | Q4 GGUF | 6.1 GB | 52.3 min | Very slowtight fit · encoder unloaded after use |
Best Video models for the Seeed Studio reComputer RK3588-30 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 48.9 min | Very slow |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 6.1 GB | 57.7 min | Very slowtight fit · encoder unloaded after use |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 5.9 GB | 8.6 h | Very slowtight fit · CPU offload |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP8 | 6.1 GB | 8.6 h | Very slowtight fit · CPU offload |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP8 | 6.0 GB | 11.4 h | Very slowtight fit · CPU offload |
Best Decision models for the Seeed Studio reComputer RK3588-30 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 120 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 2.0 GB | 2.6 s | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q6_K | 4.7 GB | 17.3 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 2.0 GB | 2.6 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 1.1 s | Slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q6_K | 4.7 GB | 17.3 s | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 5.4 GB | 16.6 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | Q8_0 | 1.7 GB | 1.9 s | Very slow |
Other products with the Rockchip RK3588 / RK3588S (8 GB)
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.