Products · IceWhale · NAS
IceWhale ZimaBoard 432
- Processor
- Intel Celeron J3455 / N3450 (Apollo Lake)
- Memory (RAM)
- 4 GB
- Launch price
- $160
- Released
- 2021
Product page (opens in a new tab)Discontinued Full AI report
Specifications
| Maker | IceWhale |
|---|---|
| Type | NAS |
| Processor | Intel Celeron J3455 / N3450 (Apollo Lake) NAS (4 GB) |
| Memory (RAM) | 4.0 GB |
| Usable for AI models | 2.0 GB |
| Memory bandwidth | 15 GB/s |
| FP16 compute | 0.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 2x SATA 3.0 (external drives); 32GB eMMC |
| NAS system | CasaOS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | LPDDR4 (soldered) · up to 4.0 GB per the maker |
| Graphics card options | PCIe: 1x PCIe 2.0 x4 (exposed). External GPU: No Thunderbolt. Maker sells an 800W OCuLink GPU Docking Station ($179.90) with a PCIe-to-OCuLink adapter…. |
| Availability | Discontinued (sold used or refurbished) |
| Notes | Intel Celeron N3450 (Apollo Lake). Apollo Lake quad-core with 4GB soldered RAM: only very small models, slowly, via Docker on CasaOS. |
| Product page | www.zimaspace.com (opens in a new tab)Discontinued |
Running AI on the IceWhale ZimaBoard 432
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 2.0 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama | In a container (Docker) |
| Open WebUI | In a container (Docker) |
Best LLMs for the IceWhale ZimaBoard 432
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 47Fair quality (C) · 47 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. | LFM3 1.7B | Q3_K_M | 1.7 GB | 3.8 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 63/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | Q4_K_M | 1.5 GB | 5.3 tok/s | Slow |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q4_K_M | 1.7 GB | 3.9 tok/s | Slow |
| 42Fair quality (C) · 42 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-VL 2B | Q3_K_M | 1.8 GB | 3.4 tok/s | Slowtight fit |
| 34Basic quality (D) · 34 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. | MiniCPM5 1B | Q4_K_M | 1.6 GB | 4.7 tok/s | Slow |
| 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. | MiniCPM-V 4.7 1B | Q4_K_M | 1.8 GB | 3.3 tok/s | Slowtight fit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q4_K_M | 1.6 GB | 4.3 tok/s | Slow |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q3_K_M | 1.8 GB | 3.5 tok/s | Slowtight fit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | Q2_K | 2.0 GB | 3.1 tok/s | Slowtight fit |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q4_K_M | 1.4 GB | 5.8 tok/s | Slow |
Best Image models for the IceWhale ZimaBoard 432
| 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 48/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 1.6 GB | 2.0 min | SlowCPU offload |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 1.3 GB | 17.8 min | Very slowCPU offload |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 1.3 GB | 17.8 min | Very slowCPU offload |
| 28Basic quality (D) · 28 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. | SD Turbo | FP16 | 1.3 GB | 71 s | SlowCPU offload |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 1.3 GB | 17.8 min | Very slowCPU offload |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 1.3 GB | 3.7 min | Very slowCPU offload |
Best Video models for the IceWhale ZimaBoard 432
None of the video models in our catalog fit in this much memory.
Best Decision models for the IceWhale ZimaBoard 432
| 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 v3.5 | Q8_0 | 1.6 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 v3 | Q8_0 | 1.6 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. | GLiNER2.5 Decide | 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-Decisions | 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 0.6B | Q8_0 | 1.6 GB | 51.4 s | Very slow |
| 79Great quality (A) · 79 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. | mxbai-rerank-large v2 | Q5_K_M | 1.9 GB | 131.8 s | Very 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 86M | Q8_0 | 1.0 GB | 26.0 s | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | Q8_0 | 1.3 GB | 42.0 s | Very slow |
Other products with the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (4 GB)
TS-251BProduct page (opens in a new tab)Discontinued
TS-253BeProduct page (opens in a new tab)Discontinued
TS-453BeProduct page (opens in a new tab)Discontinued
DS918+Product page (opens in a new tab)Discontinued- F4-421Product page (opens in a new tab)Discontinued
- F5-422Product page (opens in a new tab)Discontinued
- F2-422Product page (opens in a new tab)Discontinued
- F4-422Product page (opens in a new tab)Discontinued
Spec sources
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.