Radxa ROCK 5B+

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Specifications 32.0 GB configuration

Best LLMs for the Radxa ROCK 5B+ 32.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	Q4_K_M	25.0 GB	11.1 tok/s	Runs welltight fit
A+86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	KKAT-Coder V2.5 Dev (35B-A3B)Kuaishou	Q4_K_M	24.2 GB	11.1 tok/s	Runs well
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	OBMiniCPM-V 4.7 35B-A3BOpenBMB	Q4_K_M	24.5 GB	11.1 tok/s	Runs welltight fit
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	Q4_K_M	25.0 GB	11.1 tok/s	Runs welltight fit
A+87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NANex N2 Mini (35B-A3B)Nex-AGI	Q4_K_M	24.5 GB	11.1 tok/s	Runs welltight fit
A+85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	RFlint (40B-A2.5B)Recursive	Q4_K_M	27.4 GB	13.2 tok/s	Runs welltight fit
A+86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	ISSage-A1.5 35B-A3BInternScience	Q4_K_M	25.0 GB	11.1 tok/s	Runs welltight fit
A83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	ZAGLM-4.7 Flash (30B-A3B)Zhipu AI	Q4_K_M	22.4 GB	11.1 tok/s	Runs well
A+85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	DROrnith 1.5 35B-A3BDeepReinforce	Q4_K_M	25.0 GB	11.1 tok/s	Runs welltight fit
A82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Qwen AgentWorld 35B-A3BAlibaba	Q4_K_M	24.2 GB	11.1 tok/s	Runs well

Best Image models for the Radxa ROCK 5B+ 32.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	KKrea 2 TurboKrea	FP8	20.2 GB	9.5 min	Very slow
A+91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX 3 Image KleinBlack Forest Labs	FP16	22.4 GB	13.9 min	Very slow
A+93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	BAFibo 2.0 DevBria AI	FP16	27.7 GB	55.0 min	Very slowtight fit
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	FP16	22.7 GB	6.1 min	Very slow
A83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	Q8 GGUF	20.5 GB	5.1 min	Very slow
A+87Excellent quality (A+) · 87 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.	BERNIE-ImageBaidu	Q8 GGUF	18.9 GB	61.8 min	Very slow

Best Video models for the Radxa ROCK 5B+ 32.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	BDBernini-R A14B (video generation + editing)ByteDance	FP8	26.0 GB	26.4 h	Very slowtight fit
A70Great quality (A) · 70 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.	Wan 2.2 S2V 14B (speech to video)Alibaba	Q4 GGUF	21.6 GB	48.9 h	Very slow
A74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	THY-OmniWeaving (8.3B, unified video)Tencent	FP8	24.6 GB	19.4 h	Very slowtight fit
A73Great quality (A) · 73 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 I2V 14B 480PAlibaba	Q8 GGUF	27.2 GB	42.1 h	Very slowtight fit
A81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.5 (22B, video + audio)Lightricks	Q4 GGUF	26.8 GB	4.7 h	Very slowtight fit · encoder unloaded after use

Best Decision models for the Radxa ROCK 5B+ 32.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A78Great 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.	OAOpenAI Privacy FilterOpenAI	Q8_0	2.4 GB	120 ms	Runs great
A+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.	JAJina Reranker v3.5Jina AI	Q8_0	3.8 GB	2.6 s	Very slow
A+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	7.5 GB	17.4 s	Very slow
A+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	11.9 GB	35.4 s	Very slow
A+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.	SSkywork Reward V2 Llama 3.1 8BSkywork	Q8_0	10.4 GB	69.6 s	Very slow
A84Great 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.	JAJina Reranker v3Jina AI	Q8_0	3.8 GB	2.6 s	Very slow
A+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.	ZEzerank-2ZeroEntropy	Q8_0	7.5 GB	17.4 s	Very slow
A80Great 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.	FGLiNER2.5 DecideFastino	Q8_0	1.2 GB	1.1 s	Slow

Other products with the Rockchip RK3588 / RK3588S (32 GB)

• Orange Pi 5 PlusOPOrange Pi · Board · 4, 8, 16 or 32 GBProduct page (opens in a new tab)