Hardware · BeagleBoard

What AI models can the BeagleBone AI-64 (4 GB) run?

RAM: 4.0 GB
Usable for models: 2.8 GB
Memory bandwidth: 13 GB/s
Runs models on: CPU cores
Released: 2022

126 / 622 LLMs run Best: MiniCPM5 2B 7 / 61 Image models run Best: SD Turbo 1 / 43 Video models run Best: AnimateDiff v3 (SD 1.5) 41 / 70 Decision models run Best: Jina Reranker v3.5

Models run on the CPU cores here, so the memory’s speed and how fast those cores can read it set the pace: small models (about 1-4B) are usable, bigger ones are slow. We plan around 2.8 GB of the 4.0 GB (what Linux leaves free for a model). C7x DSP with TI’s Matrix Multiply Accelerator: 8 TOPS (INT8) for vision models compiled with TI’s TIDL tools; llama.cpp doesn’t use it.

More about this hardware

Maker	BeagleBoard
Type	Single-board computer or edge AI board
Share of memory for models	70% (what Linux typically leaves free on a board this size)
Chip	TI TDA4VM
AI accelerator	C7x DSP with TI’s Matrix Multiply Accelerator: 8 TOPS (INT8) for vision models compiled with TI’s TIDL tools; llama.cpp doesn’t use it.
Boards with this chip	BeagleBone AI-64
Memory type	4 GB LPDDR4
Bandwidth figure	12.8 GB/s, estimated, see the note below
Note	2× Cortex-A72 at 2 GHz plus six Cortex-R5F real-time cores. Built for vision and robot control; with only two CPU cores for LLMs, expect small models at a few tokens per second (estimate, assuming a 32-bit bus at 3200 MT/s).
Specifications	docs.beagleboard.org

Apps that run models well on the BeagleBone AI-64 (4 GB)

Linux on ARM boards

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 BeagleBone AI-64 (4 GB)

BeagleBone AI-64BeagleBoard · Board · 4 GBProduct page (opens in a new tab)

Best LLMs for the BeagleBone AI-64 (4 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 67/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM5 2BOpenBMB	`Q4_K_M`	2.7 GB	1.7 tok/s	Very slowtight fit
47Fair quality (C) · 47 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.	LFM3 1.7BLiquid AI	`Q3_K_M`	1.8 GB	3.3 tok/s	Slow
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Spark-X2.6 4BSparkLLM	`Q2_K`	2.8 GB	1.7 tok/s	Very slowtight fit
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-OCR 1.0 1.3BOpenBMB	`Q4_K_M`	1.7 GB	3.4 tok/s	Slow
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	TMax 4BAi2	`Q2_K`	2.8 GB	1.7 tok/s	Very slowtight fit
30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	Unlimited OCR 2 (3B-A0.6B)Baidu	`Q2_K`	2.7 GB	11.5 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 60/100 (quality, fit, speed and memory use) sets the ranking.	PaddleOCR-VL 1.6 0.9BBaidu	`Q4_K_M`	1.6 GB	4.5 tok/s	Slow
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 2.6BLiquid AI	`Q4_K_M`	2.6 GB	1.6 tok/s	Very slowtight fit
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	Jamba Reasoning 3BAI21 Labs	`Q4_K_M`	2.8 GB	1.4 tok/s	Very slowtight fit
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	TeleOCRXingChen-AGI	`Q4_K_M`	2.6 GB	3.1 tok/s	Slowtight fit
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	Jamba2 3BAI21 Labs	`Q4_K_M`	2.7 GB	1.4 tok/s	Very slowtight fit
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	Unlimited OCR (3B-A0.6B)Baidu	`Q2_K`	2.7 GB	11.5 tok/s	Runs welltight fit

Best Image models for the BeagleBone AI-64 (4 GB)

Quality	Model	Quant	Memory	Speed	Runs
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	SD TurboStability AI	`FP16`	2.6 GB	30 s	Runs welltight fit · encoder unloaded after use
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	Realistic Vision V5.1SG161222	`FP16`	2.5 GB	7.6 min	Very slowtight fit · encoder unloaded after use
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper 8Lykon	`FP16`	2.5 GB	7.6 min	Very slowtight fit · encoder unloaded after use
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	LCM DreamShaper v7Tsinghua (LCM)	`FP16`	2.5 GB	1.6 min	Slowtight fit · encoder unloaded after use
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	PixArt-Σ XL 1024PixArt	`FP16`	2.3 GB	11.8 min	Very slowCPU offload
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	Stable Diffusion 1.5Stability AI / Runway	`FP16`	2.5 GB	7.6 min	Very slowtight fit · encoder unloaded after use

Best Video models for the BeagleBone AI-64 (4 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 42/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	2.6 GB	2.6 h	Very slowtight fit · CPU offload

Best Decision models for the BeagleBone AI-64 (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 79/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	1.7 GB	25.9 s	Very slow
84Great quality (A) · 84 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.	Jina Reranker v3Jina AI	`Q8_0`	1.7 GB	25.9 s	Very slow
80Great quality (A) · 80 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.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	11.4 s	Very slow
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-large v2Mixedbread	`Q6_K`	2.1 GB	66.2 s	Very slow
80Great quality (A) · 80 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.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	19.0 s	Very slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 0.6BAlibaba	`Q8_0`	1.7 GB	25.9 s	Very slow
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	OpenAI Privacy FilterOpenAI	`Q8_0`	2.4 GB	1.2 s	Slowtight fit
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 86MMeta	`Q8_0`	1.0 GB	13.0 s	Very 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.