Products · IceWhale · NAS
IceWhale ZimaCube 2 (Standard)
- Processor
- Intel Core i3-1215U / i3-1315U
- Memory (RAM)
- 8 or 64 GB
- Launch price
- $799
- Released
- 2026
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 i3-1215U / i3-1315U | 8.0 GB | 5.2 GB | 38 GB/s | 152 of 622 | $799 |
| Intel Core i3-1215U / i3-1315U · upgraded to the maker's maximum | 64.0 GB | 54.4 GB | 38 GB/s | 216 of 622 | — |
Specifications 8.0 GB configuration
| Maker | IceWhale |
|---|---|
| Type | NAS |
| Processor | Intel Core i3-1215U / i3-1315U NAS (8 GB) |
| Memory (RAM) | 8.0 GB |
| Usable for AI models | 5.2 GB |
| Memory bandwidth | 38 GB/s |
| FP16 compute | 0.3 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 6x 3.5/2.5in SATA + 4x M.2 NVMe (7th bay) |
| NAS system | ZimaOS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5 4800 SO-DIMM (maker comparison page says DDR5 4800 and a… · 2 slots · up to 64.0 GB per the maker · 64.0 GB reported working by owners · non-ECC |
| Graphics card options | PCIe: 1x PCIe 4.0 x4 (physical x16 slot) + 1x PCIe 3.0 x2 (physical x8 slot). External GPU: Zima recommends its external GPU dock (800W OCuLink GPU Docking Station, $179.90) for larger cards; 2x rear…. Maker-supported graphics cards: NVIDIA RTX PRO 2000 16 GB (factory fitted in Creator Pack). |
| Notes | Intel Core i3-1215U. Laptop-class i3 with 8 GB as shipped; CPU/iGPU inference of small models. Upgrade RAM to 64 GB or add a slot-powered GPU for more. |
| Product page | shop.zimaspace.com (opens in a new tab) |
Running AI on the IceWhale ZimaCube 2 (Standard)
Yes, it runs AI models on the NAS itself. 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. 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 2 (Standard) 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q4_K_M | 4.2 GB | 17.1 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q3_K_M | 5.1 GB | 34.7 tok/s | Runs welltight fit |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q6_K | 4.3 GB | 39.0 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q3_K_M | 3.4 GB | 12.8 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 73/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q3_K_M | 5.1 GB | 11.3 tok/s | Runs welltight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q3_K_M | 3.3 GB | 12.4 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q3_K_M | 4.5 GB | 12.2 tok/s | Runs welltight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q4_K_M | 2.9 GB | 15.6 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q3_K_M | 5.1 GB | 11.3 tok/s | Runs welltight fit |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | Q6_K | 4.3 GB | 39.0 tok/s | Runs great |
Best Image models for the IceWhale ZimaCube 2 (Standard) 8.0 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 69/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 4.6 GB | 2.9 min | Very slowtight fit · encoder unloaded after use |
| 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 | 19.8 min | Very slowCPU offload |
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 4.2 GB | 19 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 4.4 GB | 6.8 min | Very slowCPU offload |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 3.3 GB | 11 s | Runs great |
| 78Great quality (A) · 78 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. | FLUX.2 [klein] 9B | Q4 GGUF | 4.3 GB | 6.5 min | Very slowCPU offload |
Best Video models for the IceWhale ZimaCube 2 (Standard) 8.0 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 57/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 46.5 min | Very slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 4.0 GB | 68.0 min | Very slowCPU offload |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 4.7 GB | 2.7 h | Very slowtight fit · CPU offload |
Best Decision models for the IceWhale ZimaCube 2 (Standard) 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 97 ms | Runs great |
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 1.9 GB | 2.1 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 | 1.9 GB | 2.1 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 913 ms | Slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q5_K_M | 4.2 GB | 13.8 s | Very slow |
| 80Great quality (A) · 80 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 1.5 s | Very slow |
| 68Good quality (B) · 68 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 267 ms | Runs well |
| 85Excellent quality (A+) · 85 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. | zerank-2 | Q5_K_M | 4.2 GB | 13.8 s | Very slow |
Other products with the Intel Core i3-1215U / i3-1315U NAS (8 GB)
Spec sources
- shop.zimaspace.com: zimacube-2-standard-vs-creator-pack (opens in a new tab)
- shop.zimaspace.com: zimacube-2-personal-cloud-nas (opens in a new tab)
- shop.zimaspace.com: products.json (opens in a new tab)
- zimaspace.com (opens in a new tab)
- shop.zimaspace.com: zimacube-2-standard-vs-pro (opens in a new tab)
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.