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 64.0 GB configuration
| Maker | 45HomeLab |
|---|---|
| Type | NAS |
| Processor | AMD EPYC 7002 / 7003 series NAS (64 GB) |
| Memory (RAM) | 64.0 GB |
| Usable for AI models | 54.4 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 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 | 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) 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q5_K_M | 33.4 GB | 39.7 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 52.8 GB | 35.5 tok/s | Runs welltight fit |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 27.0 GB | 40.2 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 27.0 GB | 40.2 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 26.6 GB | 40.2 tok/s | Runs great |
| 81Great quality (A) · 81 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 Coder Next (80B-A3B) | Q4_K_M | 53.8 GB | 40.2 tok/s | Runs welltight fit |
| 87Excellent quality (A+) · 87 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. | Nex N2 Mini (35B-A3B) | Q4_K_M | 26.5 GB | 40.2 tok/s | Runs great |
| 86Excellent quality (A+) · 86 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. | Sage-A1.5 35B-A3B | Q4_K_M | 27.0 GB | 40.2 tok/s | Runs great |
| 86Excellent quality (A+) · 86 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. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 26.3 GB | 40.2 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q4_K_M | 27.0 GB | 40.2 tok/s | Runs great |
Best Image models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 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 85/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 2.9 min | Very slow |
| 84Great quality (A) · 84 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 74 s | Slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | Q8 GGUF | 41.6 GB | 47.3 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 | 70.9 min | 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 | 15.1 min | Very slow |
| 93Excellent quality (A+) · 93 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. | Fibo 2.0 Dev | FP16 | 27.7 GB | 15.4 min | Very slow |
Best Video models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP8 | 48.3 GB | 56.1 min | Very slowtight fit |
| 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 | 5.3 h | Very slow |
| 85Excellent quality (A+) · 85 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. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 8.2 h | Very slow |
| 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. | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 21.0 h | Very slow |
| 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. | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 21.0 h | Very slow |
Best Decision models for the 45HomeLab HL15 2.0 (Fully Built & Burned In) 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 | 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 | 5.8 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 | 5.8 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 | 9.5 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 (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.