IceWhale ZimaCube 2 Creator Pack

Products · · NAS

IceWhale ZimaCube 2 Creator Pack

Processor
Intel Core i5-1235U / i7-1255U
Memory (RAM)
64 GB
Launch price
$2,499
Released
2026

Product page (opens in a new tab) Full AI report

Specifications

MakerIceWhale
TypeNAS
ProcessorIntel Core i5-1235U / i7-1255U NAS (64 GB)
Memory (RAM)64.0 GB
Usable for AI models54.4 GB
Memory bandwidth38 GB/s
FP16 compute0.4 TFLOPS
Runs models onCPU cores
Drive bays6x SATA 3.5/2.5in + 7th bay with 4x M.2 NVMe (3200 MB/s) + 1 onboard M.2 for OS (1TB NVMe included)
NAS systemZimaOS
Containers (Docker)Yes
Virtual machinesYes
Memory upgradeDDR5-4800 SODIMM (maker spec table says 'LPDDR5 4800MHz'… · 2 slots · up to 64.0 GB per the maker · 64.0 GB reported working by owners · non-ECC
Graphics card optionsPCIe: 2 low-profile slots per maker spec table: 1x PCIe 4.0 with 4 lanes (physical x16) and 1x PCIe 3.0 with 2…. External GPU: 2x Thunderbolt 4 (maker markets them for direct Mac/PC connection, not eGPU). Maker FAQ: 'For larger or…. 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….
NotesIntel Core i5-1235U. Ships with a 16GB-VRAM NVIDIA RTX PRO 2000 and 64GB RAM; maker says it is for 'GPU-accelerated local AI' and that it can support many compact or quantised language models.
Product pageshop.zimaspace.com (opens in a new tab)

Running AI on the IceWhale ZimaCube 2 Creator Pack

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.

Apps you can install to run models

AppHow 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

Apps that run LLMs on a NAS, with their container images

AI features from IceWhale

FeatureWhat it doesWhere 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 Creator Pack

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-A3BAlibaba 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-A3BAlibaba 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-A3BOpenBMB 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)Recursive 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)Nex-AGI 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-A3BInternScience 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-A3BDeepReinforce 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)Kuaishou 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)Apodex 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-A3BDeepReinforce Q6_K 34.6 GB 10.2 tok/s Runs well

Best Image models for the IceWhale ZimaCube 2 Creator Pack

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 TurboKrea 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 2.1Alibaba 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] 9BBlack Forest Labs 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 2512Alibaba 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-ImageBaidu 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 DevBria AI FP16 27.7 GB 40.6 min Very slow

Best Video models for the IceWhale ZimaCube 2 Creator Pack

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-2.3Lightricks 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)Lightricks 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)ByteDance 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 A14BAlibaba 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 A14BAlibaba Q8 GGUF 39.3 GB 55.4 h Very slow

Best Decision models for the IceWhale ZimaCube 2 Creator Pack

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 FilterOpenAI 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 v3.5Jina AI 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 DecideFastino 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 22MMeta 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 4BAlibaba 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 v3Jina AI 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 8BAlibaba 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 8BSkywork Q8_0 10.4 GB 34.1 s Very slow

Other products with the Intel Core i5-1235U / i7-1255U NAS (64 GB)

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.

Was this page helpful?