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 64.0 GB configuration
| Maker | IceWhale |
|---|---|
| Type | NAS |
| Processor | Intel Core i5-1235U / i7-1255U NAS (64 GB) |
| Memory (RAM) | 64.0 GB |
| Usable for AI models | 54.4 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 54.4 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 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q6_K | 34.0 GB | 10.2 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q6_K | 37.8 GB | 12.2 tok/s | Runs well |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q6_K | 33.9 GB | 10.2 tok/s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q6_K | 33.5 GB | 10.2 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q6_K | 34.6 GB | 10.2 tok/s | Runs well |
Best Image models for the IceWhale ZimaCube Pro 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 7.8 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | Q8 GGUF | 41.6 GB | 2.1 h | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 3.3 min | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | Q8 GGUF | 36.5 GB | 3.1 h | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | FP16 | 34.0 GB | 39.7 min | Very slow |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Fibo 2.0 Dev | FP16 | 27.7 GB | 40.6 min | Very slow |
Best Video models for the IceWhale ZimaCube Pro 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | Q8 GGUF | 45.6 GB | 13.8 h | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 3.2 h | Very slowtight fit |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 21.7 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 55.4 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 55.4 h | Very slow |
Best Decision models for the IceWhale ZimaCube Pro 64.0 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 | 5.8 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 | 9.5 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 | 5.8 GB | 1.3 s | Slow |
| 90Excellent quality (A+) · 90 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. | Qwen3 Reranker 8B | Q8_0 | 13.9 GB | 17.5 s | Very slow |
| 90Excellent quality (A+) · 90 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 34.1 s | Very slow |
Other products with the Intel Core i5-1235U / i7-1255U NAS (64 GB)
F4-424 MaxProduct page (opens in a new tab)
F6-424 MaxProduct 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)
NASync DXP480T PlusProduct page (opens in a new tab)
NASync DXP6800 ProProduct page (opens in a new tab)
NASync DXP8800 PlusProduct page (opens in a new tab)
NASync DXP8800 ProProduct page (opens in a new tab)
ZimaCube 2 ProProduct page (opens in a new tab)
ZimaCube 2 Creator PackProduct 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.