Hardware · AMD
What AI models can the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB) run?
- RAM
- 128 GB
- Usable for models
- 113 GB
- Memory bandwidth
- 83 GB/s
- Runs models on
- CPU cores
- Released
- 2022
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 113 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 | 88% (what the NAS system and its storage services typically leave free at this size) |
| Chip | AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) |
| AI accelerator | None. Models run on the processor cores. |
| NAS models with this chip | Asustor AS7212RDX · Asustor AS7216RDX · Asustor AS7224RDX · QNAP TVS-h1677AX · QNAP TVS-h1277AX · QNAP TVS-h877AX · QNAP QAI-16700 · QNAP TS-h3077AFU · QNAP TS-h1077AFU · QNAP TS-h2477AXU-RP · QNAP TS-h1677AXU-RP · QNAP TS-h1277AXU-RP · 45HomeLab HL15 Beast (Fully Built, ASUS ProArt / Ryzen 9) |
| Memory type | System RAM, shared with the NAS operating system and its storage services |
| Bandwidth figure | 83.2 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.asustor.com |
Apps that run models well on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)
1 product with the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)
Best LLMs for the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 76.5 GB | 17.4 tok/s | Runs well |
| 86Excellent quality (A+) · 86 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. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 57.4 GB | 23.4 tok/s | Runs well |
| 81Great quality (A) · 81 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. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 59.4 GB | 26.7 tok/s | Runs well |
| 81Great quality (A) · 81 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. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 58.4 GB | 26.7 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q3_K_M | 98.0 GB | 17.9 tok/s | Runs welltight fit |
| 79Great quality (A) · 79 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. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 59.4 GB | 26.7 tok/s | Runs well |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q4_K_M | 87.8 GB | 16.3 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Laguna S 2.1 (118B-A8B) | Q4_K_M | 82.9 GB | 10.6 tok/s | Runs well |
| 85Excellent quality (A+) · 85 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. | Flint (40B-A2.5B) | Q4_K_M | 34.1 GB | 31.5 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 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 31.7 GB | 26.7 tok/s | Runs well |
| 88Excellent quality (A+) · 88 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. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 31.3 GB | 26.7 tok/s | Runs well |
| 88Excellent quality (A+) · 88 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. | Qwen3.5 35B-A3B | Q4_K_M | 31.7 GB | 26.7 tok/s | Runs well |
Best Image models for the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 8.1 min | Very slow |
| 90Excellent quality (A+) · 90 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. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 32.2 min | Very slow |
| 88Excellent quality (A+) · 88 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. | HunyuanImage 3.0 (80B-A13B) | FP8 | 86.9 GB | 48.3 min | Very slow |
| 91Excellent quality (A+) · 91 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. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 37.1 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. | Ideogram 4 | FP16 | 57.3 GB | 22.4 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. | Qwen-Image 2.1 | FP16 | 57.0 GB | 53.7 min | Very slow |
Best Video models for the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 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 82/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 81.5 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. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 43.9 h | Very slow |
| 86Excellent quality (A+) · 86 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. | LTX-2.3 | FP16 | 75.4 GB | 6.0 h | Very slow |
| 89Excellent quality (A+) · 89 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. | MiniMax H3 (33B, video + audio) | Q8 GGUF | 68.2 GB | 17.8 h | Very slow |
| 82Great quality (A) · 82 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. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 6.0 h | Very slow |
Best Decision models for the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 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 | 41 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 | 95 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 | 318 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 | 10.5 GB | 725 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 | 10.5 GB | 725 ms | Slow |
| 66Good quality (B) · 66 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. | GLiClass Base v3 | Q8_0 | 0.8 GB | 126 ms | Runs great |
| 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 | 14.2 GB | 4.8 s | Very slow |
| 74Great quality (A) · 74 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 ModernBERT Large v3 | Q8_0 | 1.1 GB | 260 ms | Runs well |
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.