Products · IceWhale · NAS
IceWhale ZimaCube Pro
- Processor
- Intel Core i5-1235U / i7-1255U
- Memory (RAM)
- 16 or 64 GB
- Launch price
- $1,099
- Released
- 2024
Product page (opens in a new tab)Discontinued Full AI report
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| Intel Core i5-1235U / i7-1255U | 16.0 GB | 12.0 GB | 38 GB/s | 214 of 622 | $1,099 |
| Intel Core i5-1235U / i7-1255U | 64.0 GB | 54.4 GB | 38 GB/s | 257 of 622 | — |
Specifications 16.0 GB configuration
| Maker | IceWhale |
|---|---|
| Type | NAS |
| Processor | Intel Core i5-1235U / i7-1255U NAS (16 GB) |
| Memory (RAM) | 16.0 GB |
| Usable for AI models | 12.0 GB |
| Memory bandwidth | 38 GB/s |
| FP16 compute | 0.4 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 6x SATA 3.5/2.5in + 7th bay with 4x M.2 NVMe (3200 MB/s) |
| NAS system | ZimaOS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5-4800 SODIMM · 2 slots · up to 64.0 GB per the maker · 64.0 GB reported working by owners · non-ECC |
| Graphics card options | PCIe: 2 slots: PCIe 4.0 x16 physical (maker: '8 GB/s') and PCIe 3.0 (maker: '2 GB/s'); half-height cards up to…. External GPU: 2x Thunderbolt 4; ZimaOS-AI docs say full-height GPUs can be used through Thunderbolt docks or PCIe extenders…. Maker-supported graphics cards: Verified by maker: GeForce RTX 4060 Ti, GeForce RTX 3060 Ti, NVIDIA RTX A2000 12GB; Listed for ZimaOS-AI (low profile): Tesla P4, GTX 1650 LP, RTX 3050 LP, RTX 4060 LP, RTX A2000, Tesla T4, A2, RTX…. |
| Availability | Discontinued (sold used or refurbished) |
| Notes | Intel Core i5-1235U. 10-core i5 with dual-channel DDR5 up to 64GB runs 7-8B quantised models on CPU; maker documents low-profile NVIDIA GPUs (RTX A2000 12GB, RTX 4060 Ti verified) and Thunderbolt 4 for GPU inference. |
| Product page | shop.zimaspace.com (opens in a new tab)Discontinued |
Running AI on the IceWhale ZimaCube Pro
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 12.0 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. More memory is the upgrade that matters most: see the configurations.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama | From the NAS app store |
| Open WebUI | From the NAS app store |
| AnythingLLM | From the NAS app store |
| Ollama-Nvidia | From the NAS app store |
| LocalAI | From the NAS app store |
AI features from IceWhale
| Feature | What it does | Where the AI runs |
|---|---|---|
| ZimaOS AI (AI search in Files) | Optional module installed with 'zpkg install zimaos_ai' (NVIDIA) or 'zpkg install zimaos_ai_intel' (Intel iGPU); downloads a local model and adds natural-language/semantic search of files. | On the NAS |
| ZimaOS-AI (AI search / Assist in Files) | Optional ZimaOS module (zpkg install zimaos_ai for NVIDIA, zimaos_ai_intel for Intel iGPU) that extracts features from images, audio and video with a locally downloaded model and gives keyword and natural-language search. | On the NAS |
Best LLMs for the IceWhale ZimaCube Pro 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 9.5 GB | 3.8 tok/s | Slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | K2 Horizon 7B | Q6_K | 10.1 GB | 3.5 tok/s | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.1 GB | 17.3 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q3_K_M | 11.6 GB | 35.2 tok/s | Runs welltight fit |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q6_K | 9.5 GB | 3.4 tok/s | Slow |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q6_K | 10.0 GB | 3.3 tok/s | Slow |
| 76Great quality (A) · 76 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. | Ornith 1.5 9B | Q6_K | 9.7 GB | 3.3 tok/s | Slow |
| 75Great quality (A) · 75 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. | Qwen3.5 9B | Q6_K | 9.7 GB | 3.3 tok/s | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q6_K | 9.7 GB | 3.3 tok/s | Slow |
| 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q6_K | 9.2 GB | 3.6 tok/s | Slow |
Best Image models for the IceWhale ZimaCube Pro 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 10.2 GB | 12.4 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 1.6 min | Slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 10.1 GB | 5.4 min | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q4 GGUF | 11.3 GB | 6.9 min | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | Q4 GGUF | 10.1 GB | 36.8 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | Q4 GGUF | 8.0 GB | 4.1 min | Very slowencoder unloaded after use |
Best Video models for the IceWhale ZimaCube Pro 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 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. | LTX-Video 2B | FP8 | 10.8 GB | 40.6 min | Very slowtight fit |
| 83Great quality (A) · 83 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. | Bernini-R A14B (video generation + editing) | FP8 | 10.7 GB | 25.4 h | Very slowtight fit · CPU offload |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 7.8 GB | 18.7 h | Very slowCPU offload |
| 55Good quality (B) · 55 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. | Wan 2.1 T2V 1.3B | FP16 | 8.4 GB | 7.6 h | Very slowencoder unloaded after use |
| 55Good quality (B) · 55 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. | Wan 2.1 VACE 1.3B | FP16 | 10.1 GB | 8.2 h | Very slowencoder unloaded after use |
Best Decision models for the IceWhale ZimaCube Pro 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | F16 | 3.8 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 82/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 2.4 GB | 1.3 s | Slow |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 561 ms | Slow |
| 68Good quality (B) · 68 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 165 ms | Runs well |
| 90Excellent quality (A+) · 90 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. | Qwen3 Reranker 4B | Q8_0 | 6.1 GB | 8.6 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 2.4 GB | 1.3 s | Slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q6_K | 8.6 GB | 17.4 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 6.1 GB | 8.6 s | Very slow |
Other products with the Intel Core i5-1235U / i7-1255U NAS (16 GB)
AOOSTAR WTR MAX INTEL 1235U 11 Bay NASProduct page (opens in a new tab)
TBS-h574TXProduct page (opens in a new tab)
T9-500 ProProduct page (opens in a new tab)
T12-500 ProProduct page (opens in a new tab)
U8-500 PlusProduct page (opens in a new tab)
U12-500 PlusProduct page (opens in a new tab)
ZimaCube 2 ProProduct 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.