Radxa ROCK 5B+

Products · · Board

Radxa ROCK 5B+

Chip
Rockchip RK3588
Unified memory
4, 8, 16, 24 or 32 GB
Released
2024

Product page (opens in a new tab) Full AI report

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 4.0 GB 2.8 GB 34 GB/s 115 of 622 —
Rockchip RK3588 8.0 GB 6.4 GB 34 GB/s 155 of 622 —
Rockchip RK3588 16.0 GB 13.6 GB 34 GB/s 184 of 622 —
Rockchip RK3588 24.0 GB 21.1 GB 34 GB/s 203 of 622 —
Rockchip RK3588 32.0 GB 28.8 GB 34 GB/s 203 of 622 —

Specifications 24.0 GB configuration

MakerRadxa
TypeBoard
ChipRockchip RK3588 / RK3588S (24 GB)
Unified memory24.0 GB
Usable for AI models21.1 GB
Memory bandwidth34 GB/s
FP16 compute0.2 TFLOPS
NotesRK3588 with 64-bit LPDDR5, faster than the LPDDR4X boards (up to about 44 GB/s). Launched on AliExpress at $119 (16 GB) and $159 (24 GB) in July 2024 (CNX Software); Radxa publishes no US list price.
Product pageradxa.com (opens in a new tab)

Best LLMs for the Radxa ROCK 5B+ 24.0 GB

Quality Model Quant Memory Speed Runs
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba Q3_K_M 20.1 GB 14.2 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB Q3_K_M 19.7 GB 14.2 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba Q3_K_M 20.1 GB 14.2 tok/s Runs welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q3_K_M 15.3 GB 11.3 tok/s Runs well
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q3_K_M 19.7 GB 14.2 tok/s Runs welltight fit
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27BAlibaba Q4_K_M 19.8 GB 1.2 tok/s Very slowtight fit
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q3_K_M 19.4 GB 14.2 tok/s Runs welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q3_K_M 20.1 GB 14.2 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce Q3_K_M 20.1 GB 14.2 tok/s Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27BAlibaba Q4_K_M 19.8 GB 1.2 tok/s Very slowtight fit

Best Image models for the Radxa ROCK 5B+ 24.0 GB

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs Q8 GGUF 12.8 GB 16.0 min Very slow
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 20.2 GB 9.5 min Very slowtight fit
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu Q8 GGUF 15.0 GB 9.0 min Very slow
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) Q8 GGUF 13.0 GB 7.0 min Very slow
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP8 19.9 GB 4.0 min Very slowtight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-ImageBaidu Q8 GGUF 18.9 GB 61.8 min Very slowtight fit

Best Video models for the Radxa ROCK 5B+ 24.0 GB

Quality Model Quant Memory Speed Runs
83Great quality (A) · 83 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. Bernini-R A14B (video generation + editing)ByteDance FP8 20.3 GB 27.7 h Very slowtight fit · encoder unloaded after use
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 15.7 GB 20.4 h Very slowencoder unloaded after use
70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.2 S2V 14B (speech to video)Alibaba Q4 GGUF 15.6 GB 51.3 h Very slowencoder unloaded after use
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI FP16 14.7 GB 13.3 h Very slowencoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. FramePack I2V (HunyuanVideo 13B)lllyasviel FP8 19.6 GB 15.4 h Very slowtight fit · encoder unloaded after use

Best Decision models for the Radxa ROCK 5B+ 24.0 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 FilterOpenAI 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 v3.5Jina AI Q8_0 3.2 GB 2.6 s Very slow
90Excellent quality (A+) · 90 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. Qwen3 Reranker 4BAlibaba Q8_0 6.9 GB 17.4 s Very slow
90Excellent quality (A+) · 90 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. Qwen3 Reranker 8BAlibaba Q8_0 11.3 GB 35.4 s Very slow
90Excellent quality (A+) · 90 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. Skywork Reward V2 Llama 3.1 8BSkywork Q8_0 10.4 GB 69.6 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 3.2 GB 2.6 s Very slow
88Excellent quality (A+) · 88 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. zerank-2ZeroEntropy Q8_0 6.9 GB 17.4 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 DecideFastino Q8_0 1.2 GB 1.1 s Slow

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.

Was this page helpful?