Products · IceWhale · NAS
IceWhale ZimaBoard 832
- Processor
- Intel Celeron J3455 / N3450 (Apollo Lake)
- Memory (RAM)
- 8 GB
- Launch price
- $200
- 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 (8 GB) |
| Memory (RAM) | 8.0 GB |
| Usable for AI models | 5.2 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 8.0 GB per the maker · non-ECC |
| 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; maker page also lists J3455). Apollo Lake quad-core with 8GB 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 832
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 5.2 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 | From the NAS app store |
| Open WebUI | From the NAS app store |
Best LLMs for the IceWhale ZimaBoard 832
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q5_K_M | 4.3 GB | 1.1 tok/s | Very slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q5_K_M | 4.2 GB | 1.0 tok/s | Very slow |
| 64Good quality (B) · 64 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. | Nanbeige4.2 3B | Q4_K_M | 5.0 GB | 1.2 tok/s | Very slowtight fit |
| 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q5_K_M | 4.3 GB | 1.0 tok/s | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q4_K_M | 4.1 GB | 1.1 tok/s | Very slow |
| 58Good quality (B) · 58 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. | Nemotron 3.5 Bolt E4B | Q3_K_M | 5.1 GB | 1.5 tok/s | Very slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 4.1 GB | 1.1 tok/s | Very slow |
| 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. | Gemma 4 E4B | Q3_K_M | 5.1 GB | 1.5 tok/s | Very slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 4B | Q4_K_M | 4.1 GB | 1.1 tok/s | Very slow |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL-Cowork 4.7B | Q4_K_M | 5.1 GB | 1.1 tok/s | Very slowtight fit |
Best Image models for the IceWhale ZimaBoard 832
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q8 GGUF | 4.3 GB | 1.6 h | Very slowCPU offload |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 4.6 GB | 14.4 min | Very slowtight fit · encoder unloaded after use |
| 82Great quality (A) · 82 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. | Z-Image Turbo | FP8 | 4.4 GB | 33.4 min | Very slowCPU offload |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q4 GGUF | 4.1 GB | 6.5 h | Very slowCPU offload |
| 81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | Q8 GGUF | 4.1 GB | 4.0 h | Very slowCPU offload |
| 80Great quality (A) · 80 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. | Z-Image | FP8 | 4.4 GB | 3.8 h | Very slowCPU offload |
Best Video models for the IceWhale ZimaBoard 832
| 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 55/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 3.8 h | Very slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 4.0 GB | 5.6 h | Very slowCPU offload |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 4.7 GB | 13.3 h | Very slowtight fit · CPU offload |
Best Decision models for the IceWhale ZimaBoard 832
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q5_K_M | 4.2 GB | 344.0 s | Very slow |
| 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 | 1.9 GB | 51.4 s | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q5_K_M | 4.2 GB | 344.0 s | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q6_K | 4.4 GB | 329.6 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 | 1.9 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 v2 | Q8_0 | 2.7 GB | 132.0 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. | d1 3B | Q8_0 | 4.4 GB | 134.3 s | Very slow |
| 81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q5_K_M | 4.3 GB | 194.8 s | Very slow |
Other products with the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 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
DS1019+Product 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
- F2-422Product page (opens in a new tab)Discontinued
- F4-422Product page (opens in a new tab)Discontinued
- F8-422Product page (opens in a new tab)Discontinued
ZimaBoard SEProduct page (opens in a new tab)
ZimaBlade 7700Product page (opens in a new tab)Discontinued
ZimaBoard SE 864Product page (opens in a new tab)
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.