Products · 45HomeLab · NAS
45HomeLab HL15 2.0 (Fully Built & Burned In)
- Processor
- AMD EPYC 7002 / 7003 series
- Memory (RAM)
- 16, 32, 64, 128, 256 or 512 GB
- Launch price
- $2,920
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 |
|---|---|---|---|---|---|
| AMD EPYC 7002 / 7003 series | 16.0 GB | 12.0 GB | 205 GB/s | 352 of 619 | $2,920 |
| AMD EPYC 7002 / 7003 series | 32.0 GB | 26.2 GB | 205 GB/s | 395 of 619 | — |
| AMD EPYC 7002 / 7003 series | 64.0 GB | 54.4 GB | 205 GB/s | 420 of 619 | — |
| AMD EPYC 7002 / 7003 series | 128 GB | 113 GB | 205 GB/s | 441 of 619 | — |
| AMD EPYC 7002 / 7003 series | 256 GB | 230 GB | 205 GB/s | 457 of 619 | — |
| AMD EPYC 7002 / 7003 series | 512 GB | 471 GB | 205 GB/s | 459 of 619 | — |
Specifications 256 GB configuration
| Maker | 45HomeLab |
|---|---|
| Type | NAS |
| Processor | AMD EPYC 7002 / 7003 series NAS (256 GB) |
| Memory (RAM) | 256 GB |
| Usable for AI models | 230 GB |
| Memory bandwidth | 205 GB/s |
| FP16 compute | 1.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 15x 3.5" SATA/SAS (direct-wired backplane), 4U |
| NAS system | Rocky Linux 9 with Houston UI |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 ECC RDIMM/LRDIMM · 8 slots · up to 512 GB per the maker · ECC |
| Graphics card options | PCIe: ASRock Rack ROMED8-2T motherboard (multiple full-length PCIe slots; exact count not stated on the store page…. |
| Notes | AMD EPYC 7252 (options: EPYC 7272, 7282, 7452). Server-class AMD EPYC with 8-channel DDR4 and up to 512 GB ECC RAM, plus full-size PCIe slots and a 1000 W ATX PSU, so one or more NVIDIA GPUs can be added. No AI app is preinstalled: you run Ollama in Docker/Podman on Rocky Linux, or install TrueNAS/Proxmox/Unraid. |
| Product page | store.45homelab.com (opens in a new tab) |
Running AI on the 45HomeLab HL15 2.0 (Fully Built & Burned In)
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 230 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 | In a container (Docker) |
| Open WebUI | In a container (Docker) |
| LocalAI | In a container (Docker) |
Best LLMs for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 256 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q4_K_M | 129 GB | 21.6 tok/s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.7 (230B-A10B) | Q5_K_M | 183 GB | 11.1 tok/s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.7 Flash (198B-A11B) | Q5_K_M | 162 GB | 10.1 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.5 (230B-A10B) | Q5_K_M | 183 GB | 11.1 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Inkling Small (276B-A12B) | Q4_K_M | 182 GB | 11.2 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.5 Flash (196B-A11B) | Q5_K_M | 161 GB | 10.1 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.1 (230B-A10B) | Q5_K_M | 183 GB | 11.1 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (284B-A13B) | Q4_K_M | 205 GB | 10.4 tok/s | Runs welltight fit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2 (230B-A10B) | Q5_K_M | 183 GB | 11.1 tok/s | Runs well |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (April 2026) | Q4_K_M | 197 GB | 10.4 tok/s | Runs welltight fit |
Best Image models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 256 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 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. | HunyuanImage 3.0 (80B-A13B) | FP16 | 170 GB | 41.1 min | Very slow |
| 92Excellent quality (A+) · 92 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. | Cosmos3-Super Text2Image (64B) | FP16 | 133 GB | 27.4 min | Very slow |
| 92Excellent quality (A+) · 92 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. | FLUX.2 [dev] | FP16 | 116 GB | 24.7 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 2.9 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 17.1 min | Very slow |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 41.1 min | Very slow |
Best Video models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 256 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 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. | Cosmos3-Super Image2Video (64B) | FP16 | 139 GB | 25.7 h | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP16 | 113 GB | 11.9 h | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 62.3 min | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 33.6 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 4.6 h | Very slow |
Best Decision models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 256 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 | 44 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 103 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 345 ms | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 19.9 GB | 780 ms | Slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 19.9 GB | 780 ms | Slow |
| 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 | 23.6 GB | 5.2 s | Very slow |
| 66Good quality (B) · 66 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. | GLiClass Base v3 | Q8_0 | 0.8 GB | 136 ms | Runs well |
| 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 574 ms | Slow |
Other products with the AMD EPYC 7002 / 7003 series NAS (256 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.