Orange Pi 5 Plus

Hardware · Rockchip

What AI models can the Rockchip RK3588 NAS (4 GB) run?

RAM
4.0 GB
Usable for models
2.0 GB
Memory bandwidth
34 GB/s
Runs models on
CPU cores
Released
2022

A NAS with this chip runs models on its processor cores, so memory speed sets the pace: small models (about 1-4B) answer at a usable speed, bigger ones are slow. We plan around 2.0 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.

More about this hardware

MakerRockchip
TypeNAS (network attached storage) processor
Share of memory for models50% (what the NAS system and its storage services typically leave free at this size)
ChipRockchip RK3588
AI acceleratorA 6 TOPS NPU and Mali-G610 graphics; language models normally run on the processor cores.
NAS models with this chipUnifyDrive UT2 · StationPC DA400 · DigiEra OmniCore (Base) · Zettlab D4 · Zettlab D6 · FriendlyElec CM3588 NAS Kit · FriendlyElec CM3588 Plus NAS Kit · Zettlab ZettLab D4 · Zettlab ZettLab D6 · QNAP TS-AI642 · UGREEN NASync DH4300 Plus
Memory typeSystem RAM, shared with the NAS operating system and its storage services
Bandwidth figure33.8 GB/s, estimated, see the note below
NoteOne profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work.
Specificationsunifydrive.com

Apps that run models well on the Rockchip RK3588 NAS (4 GB)

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

1 product with the Rockchip RK3588 NAS (4 GB)

Best LLMs for the Rockchip RK3588 NAS (4 GB)

Quality Model Quant Memory Speed Runs
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7BLiquid AI Q4_K_M 1.9 GB 21.0 tok/s Runs welltight fit
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9BBaidu Q4_K_M 1.5 GB 37.8 tok/s Runs great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3BOpenBMB Q4_K_M 1.7 GB 27.9 tok/s Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2BLiquid AI Q3_K_M 1.8 GB 24.4 tok/s Runs welltight fit
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1BOpenBMB Q4_K_M 1.6 GB 33.6 tok/s Runs great
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1BOpenBMB Q3_K_M 1.6 GB 30.3 tok/s Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 1.2B InstructLiquid AI Q3_K_M 1.4 GB 40.1 tok/s Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8BAlibaba Q4_K_M 1.4 GB 41.7 tok/s Runs great
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. TMax 2BAi2 Q3_K_M 1.8 GB 25.0 tok/s Runs welltight fit
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 2BAlibaba Q3_K_M 2.0 GB 20.7 tok/s Runs welltight fit
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. LFM2 1.2BLiquid AI Q3_K_M 1.4 GB 40.1 tok/s Runs great
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. EXAONE 4.0 1.2BLG AI Research Q3_K_M 1.9 GB 36.7 tok/s Runs welltight fit

Best Image models for the Rockchip RK3588 NAS (4 GB)

Quality Model Quant Memory Speed Runs
39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. SDXL TurboStability AI FP8 1.6 GB 34 s Runs wellCPU offload
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. SD TurboStability AI FP16 1.3 GB 20 s Runs wellCPU offload
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. Realistic Vision V5.1SG161222 FP16 1.3 GB 5.0 min Very slowCPU offload
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. DreamShaper 8Lykon FP16 1.3 GB 5.0 min Very slowCPU offload
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. LCM DreamShaper v7Tsinghua (LCM) FP16 1.3 GB 62 s SlowCPU offload
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. Stable Diffusion 1.5Stability AI / Runway FP16 1.3 GB 5.0 min Very slowCPU offload

Best Video models for the Rockchip RK3588 NAS (4 GB)

None of the video models in our catalog fit in this much memory.

Best Decision models for the Rockchip RK3588 NAS (4 GB)

Quality Model Quant Memory Speed Runs
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 v3.5Jina AI Q8_0 1.6 GB 3.5 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 v3Jina AI Q8_0 1.6 GB 3.5 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. GLiNER2.5 DecideFastino Q8_0 1.2 GB 1.5 s Very slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI Q8_0 1.7 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 78/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 0.6BAlibaba Q8_0 1.6 GB 3.5 s Very slow
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta Q8_0 1.0 GB 1.8 s Very slow
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 22MMeta Q8_0 0.7 GB 452 ms Slow
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GLiClass ModernBERT Large v3Knowledgator Q8_0 1.1 GB 1.3 s Slow

Best LLMs by task on this hardware Open in Model Finder

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.

Was this page helpful?