What AI models can the LattePanda 3 Delta (8 GB) run?

Unified memory: 8.0 GB
Usable for models: 4.0 GB
Memory bandwidth: 12 GB/s
Runs models on: GPU (SYCL)
Released: 2022

208 / 622 LLMs run Best: MiniCPM5 2B 29 / 61 Image models run Best: SD Turbo 1 / 43 Video models run Best: AnimateDiff v3 (SD 1.5) 48 / 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 4.0 GB of the 8.0 GB (what the operating system leaves free for a model). Intel UHD Graphics (24 EUs); 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 Celeron N5105
AI accelerator	Intel UHD Graphics (24 EUs); no NPU.
Boards with this chip	LattePanda 3 Delta 864
Memory type	8 GB LPDDR4-2933
Bandwidth figure	11.7 GB/s, estimated, see the note below
Note	4-core Celeron N5105. LattePanda doesn’t publish the memory bus; reviews describe it as single-channel, so we assume 32-bit (11.7 GB/s, estimate). Small models only.
Specifications	docs.lattepanda.com

Apps that run models well on the LattePanda 3 Delta (8 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 LattePanda 3 Delta (8 GB)

LattePanda 3 Delta 864LattePanda · Board · 8 GBProduct page (opens in a new tab)

Best LLMs for the LattePanda 3 Delta (8 GB)

Quality	Model	Quant	Memory	Speed	Runs
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM5 2BOpenBMB	`Q6_K`	3.3 GB	3.0 tok/s	Slow
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron Labs Dory 1.0 4BNVIDIA	`Q3_K_M`	3.3 GB	3.6 tok/s	Slow
55Good quality (B) · 55 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.	Spark-X2.6 4BSparkLLM	`Q3_K_M`	3.2 GB	3.5 tok/s	Slow
52Fair quality (C) · 52 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.	Gemma 4 E2BGoogle	`Q3_K_M`	3.5 GB	6.2 tok/s	Slowtight fit
36Basic quality (D) · 36 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.	Unlimited OCR 2 (3B-A0.6B)Baidu	`Q3_K_M`	3.1 GB	22.0 tok/s	Runs well
51Fair quality (C) · 51 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.	TMax 4BAi2	`Q3_K_M`	3.3 GB	3.4 tok/s	Slow
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 4BAlibaba	`Q3_K_M`	3.5 GB	3.0 tok/s	Slowtight fit
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Unlimited OCR (3B-A0.6B)Baidu	`Q3_K_M`	3.1 GB	22.0 tok/s	Runs well
50Fair quality (C) · 50 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.	Agents-A1 4BInternScience	`Q3_K_M`	3.4 GB	3.1 tok/s	Slowtight fit
48Fair quality (C) · 48 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.	Fara 1.5 4BMicrosoft	`Q3_K_M`	3.4 GB	3.1 tok/s	Slowtight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	LFM3-VL 2BLiquid AI	`Q4_K_M`	2.2 GB	5.7 tok/s	Slow
43Fair quality (C) · 43 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.	Granite 4.2 3BIBM	`Q3_K_M`	3.4 GB	3.9 tok/s	Slow

Best Image models for the LattePanda 3 Delta (8 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 67/100 (quality, fit, speed and memory use) sets the ranking.	SD TurboStability AI	`FP16`	3.3 GB	5.7 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q4 GGUF`	3.4 GB	10.6 min	Very slowCPU offload
39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	SDXL TurboStability AI	`FP8`	3.4 GB	10 s	Runs welltight fit · encoder unloaded after use
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	LCM DreamShaper v7Tsinghua (LCM)	`FP16`	2.8 GB	18 s	Runs well
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	3.5 GB	84 s	Slowtight fit · CPU offload
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	Realistic Vision V5.1SG161222	`FP16`	2.8 GB	86 s	Slow

Best Video models for the LattePanda 3 Delta (8 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 47/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	2.6 GB	31.0 min	SlowCPU offload

Best Decision models for the LattePanda 3 Delta (8 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 88/100 (quality, fit, speed and memory use) sets the ranking.	OpenAI Privacy FilterOpenAI	`Q8_0`	2.4 GB	45 ms	Runs great
68Good quality (B) · 68 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.	Llama Prompt Guard 2 22MMeta	`Q8_0`	0.7 GB	122 ms	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	410 ms	Slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	1.8 GB	1.0 s	Slow
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`Q8_0`	1.8 GB	1.0 s	Slow
80Great quality (A) · 80 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.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	684 ms	Slow
66Good quality (B) · 66 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.	GLiClass Base v3Knowledgator	`Q8_0`	0.8 GB	162 ms	Runs well
74Great quality (A) · 74 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.	GLiClass ModernBERT Large v3Knowledgator	`Q8_0`	1.1 GB	336 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.