Hardware · AMD
What AI models can the AMD Ryzen Embedded V1500B NAS (64 GB) run?
- RAM
- 64.0 GB
- Usable for models
- 54.4 GB
- Memory bandwidth
- 19 GB/s
- Runs models on
- CPU cores
- Released
- 2018
A NAS with this chip runs models on its processor cores, so memory speed sets the pace: small models (about 1-4B) answer at a usable speed, bigger ones are slow. We plan around 54.4 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.
More about this hardware
| Maker | AMD |
|---|---|
| Type | NAS (network attached storage) processor |
| Share of memory for models | 85% (what the NAS system and its storage services typically leave free at this size) |
| Chip | AMD Ryzen Embedded V1500B |
| AI accelerator | None. Models run on the processor cores. |
| NAS models with this chip | QNAP TS-873A · QNAP TS-673A · QNAP TS-473A · QNAP TS-h973AX · QNAP TS-1673AU-RP · QNAP TS-1273AU-RP · QNAP TS-873AU · QNAP TS-873AU-RP · QNAP TS-873AeU-RP · QNAP TS-873AeU · Synology RS1226RP+ · Synology RS1226+ · Synology RS826RP+ · Synology RS826+ · Synology RS1221RP+ · Synology RS1221+ · Synology RS2821RP+ · Synology RS2421RP+ · Synology RS2421+ · Synology RS822RP+ · Synology RS822+ · Synology DS2422+ · Synology DS1825+ · Synology DS1825neo+ · Synology DS1525+ · Synology DS1525neo+ · Synology DS925+ · Synology DS925neo+ · Synology DS1821+ · Synology DS1621+ |
| Memory type | System RAM, shared with the NAS operating system and its storage services |
| Bandwidth figure | 19.2 GB/s, estimated, see the note below |
| Note | One profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work. |
| Specifications | www.qnap.com |
Apps that run models well on the AMD Ryzen Embedded V1500B NAS (64 GB)
10 products with the AMD Ryzen Embedded V1500B NAS (64 GB)
TS-873AProduct page (opens in a new tab)
TS-673AProduct page (opens in a new tab)
TS-473AProduct page (opens in a new tab)
TS-h973AXProduct page (opens in a new tab)
TS-1673AU-RPProduct page (opens in a new tab)
TS-1273AU-RPProduct page (opens in a new tab)
TS-873AUProduct page (opens in a new tab)Discontinued
TS-873AU-RPProduct page (opens in a new tab)Discontinued
TS-873AeU-RPProduct page (opens in a new tab)
TS-873AeUProduct page (opens in a new tab)
Best LLMs for the AMD Ryzen Embedded V1500B NAS (64 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 95Excellent quality (A+) · 95 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. | Nanbeige4.3 33B | Q8_0 | 41.8 GB | 0.3 tok/s | Very slow |
| 95Excellent quality (A+) · 95 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. | Qwen3.8 27B | Q8_0 | 34.9 GB | 0.4 tok/s | Very slow |
| 94Excellent quality (A+) · 94 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. | Qwen3.6 27B | Q8_0 | 34.9 GB | 0.4 tok/s | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 52.8 GB | 5.6 tok/s | Slowtight fit |
| 93Excellent quality (A+) · 93 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. | Qwen3.5 27B | Q8_0 | 34.9 GB | 0.4 tok/s | Very slow |
| 92Excellent quality (A+) · 92 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. | Muse Glimmer 30B | Q8_0 | 36.6 GB | 0.3 tok/s | Very slow |
| 91Excellent quality (A+) · 91 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. | Gemma 4 31B | Q8_0 | 39.7 GB | 0.3 tok/s | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q6_K | 26.5 GB | 3.5 tok/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. | TMax 27B | Q8_0 | 34.5 GB | 0.4 tok/s | Very slow |
| 88Excellent quality (A+) · 88 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. | Fara 1.5 27B | Q8_0 | 34.5 GB | 0.4 tok/s | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q6_K | 28.6 GB | 3.1 tok/s | Slow |
| 86Excellent quality (A+) · 86 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. | UI-Mate 27B | Q8_0 | 34.5 GB | 0.4 tok/s | Very slow |
Best Image models for the AMD Ryzen Embedded V1500B NAS (64 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 | 12.2 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 | 3.3 h | Very slow |
| 84Great quality (A) · 84 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 5.1 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 | 4.9 h | Very slow |
| 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. | ERNIE-Image | FP16 | 34.0 GB | 62.5 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 | 63.9 min | Very slow |
Best Video models for the AMD Ryzen Embedded V1500B NAS (64 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 | 21.8 h | Very slow |
| 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 | 34.1 h | Very slow |
| 87Excellent quality (A+) · 87 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. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 5.0 h | Very slowtight fit |
| 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 | 87.2 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 | 87.2 h | Very slow |
Best Decision models for the AMD Ryzen Embedded V1500B NAS (64 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 85/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 159 ms | Runs well |
| 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 4B | Q8_0 | 9.5 GB | 23.3 s | Very slow |
| 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 | 5.8 GB | 3.5 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. | Qwen3 Reranker 8B | Q8_0 | 13.9 GB | 47.4 s | Very slow |
| 90Excellent quality (A+) · 90 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 92.8 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 9.5 GB | 23.3 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 5.8 GB | 3.5 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 1.5 s | Very slow |
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.