What AI models can the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 GB) run?

RAM: 6.0 GB
Usable for models: 3.5 GB
Memory bandwidth: 15 GB/s
Runs models on: CPU cores
Released: 2016

158 / 622 LLMs run Best: Nemotron Labs Dory 1.0 4B 24 / 61 Image models run Best: FLUX.2 [klein] 4B 1 / 43 Video models run Best: AnimateDiff v3 (SD 1.5) 48 / 70 Decision models run Best: Jina Reranker v3.5

A NAS with this chip runs models on its processor cores, so memory speed sets the pace: small models (about 1-4B) answer at a usable speed, bigger ones are slow. We plan around 3.5 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.

More about this hardware

Maker	Intel
Type	NAS (network attached storage) processor
Share of memory for models	58% (what the NAS system and its storage services typically leave free at this size)
Chip	Intel Celeron J3455 / N3450 (Apollo Lake)
AI accelerator	None. Models run on the processor cores.
NAS models with this chip	QNAP TS-251B · QNAP TS-253Be · QNAP TS-453Be · Synology DS620slim · Synology DS1019+ · Synology DS918+ · Synology DS718+ · Synology DS218+ · TerraMaster F2-221 · TerraMaster F5-221 · TerraMaster F4-421 · TerraMaster F5-422 · TerraMaster F2-422 · TerraMaster F4-422 · TerraMaster F8-422 · IceWhale ZimaBoard SE · IceWhale ZimaBlade 7700 · IceWhale ZimaBoard 832 · IceWhale ZimaBoard SE 864 · IceWhale ZimaBoard SE 1664 · IceWhale ZimaBlade 3760 · IceWhale ZimaBoard 432
Memory type	System RAM, shared with the NAS operating system and its storage services
Bandwidth figure	14.9 GB/s, estimated, see the note below
Note	One profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work.
Specifications	www.qnap.com

Apps that run models well on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 GB)

Linux

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

5 products with the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 GB)

DS620slimSynology · NAS · 6 GBProduct page (opens in a new tab)Discontinued
DS718+Synology · NAS · 6 GBProduct page (opens in a new tab)Discontinued
DS218+Synology · NAS · 6 GBProduct page (opens in a new tab)Discontinued
F2-221TerraMaster · NAS · 6 GBProduct page (opens in a new tab)Discontinued
F5-221TerraMaster · NAS · 6 GBProduct page (opens in a new tab)Discontinued

Best LLMs for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 GB)

Quality	Model	Quant	Memory	Speed	Runs
57Good quality (B) · 57 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.	Nemotron Labs Dory 1.0 4BNVIDIA	`Q3_K_M`	3.3 GB	1.7 tok/s	Very slowtight fit
55Good quality (B) · 55 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.	Spark-X2.6 4BSparkLLM	`Q3_K_M`	3.2 GB	1.6 tok/s	Very slowtight fit
52Fair quality (C) · 52 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.	Qwen3.5 4BAlibaba	`Q3_K_M`	3.4 GB	1.4 tok/s	Very slowtight fit
51Fair quality (C) · 51 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 4BAi2	`Q3_K_M`	3.2 GB	1.6 tok/s	Very slowtight fit
50Fair quality (C) · 50 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.	Agents-A1 4BInternScience	`Q3_K_M`	3.4 GB	1.4 tok/s	Very slowtight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Fara 1.5 4BMicrosoft	`Q3_K_M`	3.4 GB	1.4 tok/s	Very slowtight fit
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Unlimited OCR 2 (3B-A0.6B)Baidu	`Q3_K_M`	3.0 GB	10.6 tok/s	Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM5 2BOpenBMB	`Q2_K`	2.2 GB	3.3 tok/s	Slow
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3 Nano 4BNVIDIA	`Q4_K_M`	3.4 GB	1.3 tok/s	Very slowtight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q2_K`	3.0 GB	3.6 tok/s	Slowtight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	LFM3 1.7BLiquid AI	`Q3_K_M`	1.8 GB	3.8 tok/s	Slow
41Fair quality (C) · 41 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.	LFM2.5-VL 3BLiquid AI	`Q4_K_M`	2.9 GB	1.6 tok/s	Very slow

Best Image models for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 GB)

Quality	Model	Quant	Memory	Speed	Runs
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`Q4 GGUF`	2.9 GB	17.8 min	Very slowCPU offload
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	Realistic Vision V5.1SG161222	`FP16`	2.8 GB	13.7 min	Very slow
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	MOSS-Image SFTOpenMOSS	`Q4 GGUF`	3.3 GB	4.2 h	Very slowtight fit · CPU offload
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper 8Lykon	`FP16`	2.8 GB	13.7 min	Very slow
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	Stable Diffusion 1.5Stability AI / Runway	`FP16`	2.8 GB	13.7 min	Very slow
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	LCM DreamShaper v7Tsinghua (LCM)	`FP16`	2.8 GB	2.9 min	Very slow

Best Video models for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 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 44/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	2.6 GB	4.9 h	Very slowCPU offload

Best Decision models for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (6 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	51.4 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	51.4 s	Very slow
82Great quality (A) · 82 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.	mxbai-rerank-large v2Mixedbread	`Q8_0`	2.6 GB	132.0 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.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	22.7 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.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	38.0 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	51.4 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.	zerank-1 smallZeroEntropy	`Q8_0`	2.9 GB	147.4 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	2.3 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.