What AI models can the UP Squared Pro 7000 (16 GB) run?

Unified memory: 16.0 GB
Usable for models: 8.0 GB
Memory bandwidth: 38 GB/s
Runs models on: GPU (SYCL)
Released: 2023

338 / 622 LLMs run Best: K2 Horizon 7B 49 / 61 Image models run Best: FLUX.2 [klein] 4B 7 / 43 Video models run Best: LTX-Video 2B 62 / 70 Decision models run Best: OpenAI Privacy Filter

Models run on the GPU (SYCL) here, sharing the board’s memory with the system. We plan around 8.0 GB of the 16.0 GB (what the operating system leaves free for a model). Intel UHD Graphics (32 EUs on the Core i3-N305); no NPU.

More about this hardware

Maker	Intel
Type	Single-board computer or edge AI board
GPU share of memory	50% (what the GPU can typically be given for a model)
Chip	Intel Core i3-N305
AI accelerator	Intel UHD Graphics (32 EUs on the Core i3-N305); no NPU.
Boards with this chip	UP Squared Pro 7000 (Core i3-N305, Atom x7425E, N97 or N50)
Memory type	LPDDR5-4800 (up to 5200 MT/s on smaller versions), 64-bit
Bandwidth figure	38.4 GB/s, the chip’s rated memory speed
Note	Figures for the 8-core Core i3-N305 version; the N97, N50 and Atom x7425E versions have fewer cores and graphics units. GPU figure from 32 EUs at 1.25 GHz.
Specifications	up-board.org

Apps that run models well on the UP Squared Pro 7000 (16 GB)

Windows

Linux

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 UP Squared Pro 7000 (16 GB)

UP Squared Pro 7000AAEON UP · Board · 4, 8 or 16 GBProduct page (opens in a new tab)

Best LLMs for the UP Squared Pro 7000 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	K2 Horizon 7BInstitute of Foundation Models	`Q4_K_M`	7.9 GB	4.0 tok/s	Slowtight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	6.3 GB	25.3 tok/s	Runs well
74Great quality (A) · 74 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.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	7.2 GB	3.8 tok/s	Slowtight fit
74Great quality (A) · 74 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.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	7.6 GB	3.7 tok/s	Slowtight fit
73Great quality (A) · 73 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.	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	7.4 GB	3.7 tok/s	Slowtight fit
72Great quality (A) · 72 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.	Qwen3.5 9BAlibaba	`Q4_K_M`	7.4 GB	3.7 tok/s	Slowtight fit
71Great quality (A) · 71 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.	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	7.4 GB	3.7 tok/s	Slowtight fit
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	TMax 9BAi2	`Q5_K_M`	7.9 GB	3.3 tok/s	Slowtight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q3_K_M`	7.3 GB	17.6 tok/s	Runs welltight fit
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	`Q3_K_M`	7.8 GB	3.9 tok/s	Slowtight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q3_K_M`	5.3 GB	10.3 tok/s	Runs well
58Good quality (B) · 58 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.	Gemma 4 E2BGoogle	`Q4_K_M`	4.4 GB	15.7 tok/s	Runs well

Best Image models for the UP Squared Pro 7000 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	6.2 GB	39 s	Runs wellencoder unloaded after use
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q4 GGUF`	5.7 GB	4.9 min	Very slowencoder unloaded after use
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	6.1 GB	2.2 min	Slowencoder unloaded after use
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	SDXL-Lightning (4-step)ByteDance	`FP8`	5.6 GB	26 s	Runs well
56Good quality (B) · 56 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.	DreamShaper XL v2 TurboLykon	`FP8`	5.6 GB	48 s	Slow
79Great quality (A) · 79 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.	ERNIE-Image TurboBaidu	`Q4 GGUF`	7.4 GB	2.8 min	Very slowtight fit · encoder unloaded after use

Best Video models for the UP Squared Pro 7000 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	6.1 GB	16.1 min	Slowencoder unloaded after use
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	13.7 min	Slow
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	7.1 GB	2.6 h	Very slowtight fit · encoder unloaded after use
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	6.2 GB	38.7 min	Slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5BZhipu AI	`FP8`	5.9 GB	2.4 h	Very slowCPU offload

Best Decision models for the UP Squared Pro 7000 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	OpenAI Privacy FilterOpenAI	`F16`	3.8 GB	27 ms	Runs great
80Great quality (A) · 80 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.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	198 ms	Runs well
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 22MMeta	`F16`	0.8 GB	69 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	2.1 GB	473 ms	Slow
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GLiClass ModernBERT Large v3Knowledgator	`Q8_0`	1.1 GB	162 ms	Runs well
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GTE Reranker ModernBERT BaseAlibaba	`Q8_0`	0.8 GB	123 ms	Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GLiClass Base v3Knowledgator	`F16`	1.0 GB	90 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`Q8_0`	2.1 GB	473 ms	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.