What AI models can the UP Squared Pro 7000 (4 GB) run?

Unified memory: 4.0 GB
Usable for models: 2.0 GB
Memory bandwidth: 38 GB/s
Runs models on: GPU (SYCL)
Released: 2023

82 / 622 LLMs run Best: LFM3 1.7B 6 / 61 Image models run Best: SDXL Turbo 0 / 43 Video models run None fit 36 / 70 Decision models run Best: GLiNER2.5 Decide

Models run on the GPU (SYCL) here, sharing the board’s memory with the system. We plan around 2.0 GB of the 4.0 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 (4 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 (4 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 (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	20.8 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	37.5 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	27.7 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	24.2 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	33.3 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	30.0 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	39.8 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	41.4 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	24.8 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	20.5 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	39.8 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	36.4 tok/s	Runs welltight fit

Best Image models for the UP Squared Pro 7000 (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 59/100 (quality, fit, speed and memory use) sets the ranking.	SDXL TurboStability AI	`FP8`	1.6 GB	7.2 s	Runs greatCPU offload
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`	1.3 GB	4.3 s	Runs greatCPU offload
30Basic quality (D) · 30 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.	LCM DreamShaper v7Tsinghua (LCM)	`FP16`	1.3 GB	13 s	Runs greatCPU offload
42Fair quality (C) · 42 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.	Realistic Vision V5.1SG161222	`FP16`	1.3 GB	64 s	SlowCPU offload
40Fair quality (C) · 40 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.	DreamShaper 8Lykon	`FP16`	1.3 GB	64 s	SlowCPU offload
35Basic quality (D) · 35 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.	Stable Diffusion 1.5Stability AI / Runway	`FP16`	1.3 GB	64 s	SlowCPU offload

Best Video models for the UP Squared Pro 7000 (4 GB)

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

Best Decision models for the UP Squared Pro 7000 (4 GB)

Quality	Model	Quant	Memory	Speed	Runs
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`	1.6 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`	1.6 GB	473 ms	Slow
80Great quality (A) · 80 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.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	328 ms	Runs well

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.