Products · TerraMaster · NAS
TerraMaster U8-423
- Processor
- Intel Celeron N5105 / N5095
- Memory (RAM)
- 4 or 32 GB
- Launch price
- $1,100
- Released
- 2022
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 |
|---|---|---|---|---|---|
| Intel Celeron N5105 / N5095 | 4.0 GB | 2.0 GB | 24 GB/s | 52 of 622 | $1,100 |
| Intel Celeron N5105 / N5095 · upgraded to the maker's maximum | 32.0 GB | 26.2 GB | 24 GB/s | 72 of 622 | — |
Specifications 4.0 GB configuration
| Maker | TerraMaster |
|---|---|
| Type | NAS |
| Processor | Intel Celeron N5105 / N5095 NAS (4 GB) |
| Memory (RAM) | 4.0 GB |
| Usable for AI models | 2.0 GB |
| Memory bandwidth | 24 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 8x SATA + 1x M.2 NVMe (rackmount) |
| NAS system | TOS 6 |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 SODIMM (non-ECC) · 2 slots · up to 32.0 GB per the maker · non-ECC |
| Notes | Intel Celeron N5095. CPU only: 4-core low-power chip, no NPU and no GPU slot. Ollama in Docker is the maker's suggested route; expect small models (1-4B, quantised) at slow speeds. No tokens-per-second benchmark was found for this model. Ships with 4 GB, so a memory upgrade is needed first. |
| Product page | www.terra-master.com (opens in a new tab) |
Running AI on the TerraMaster U8-423
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 2.0 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) |
AI features from TerraMaster
| Feature | What it does | Where the AI runs |
|---|---|---|
| Terra Photos (TerraMaster Photos) | Photo library with face and scene recognition; the maker says the AI processing uses a local model on the NAS. This is an image classifier, not a chat model. | On the NAS |
Best LLMs for the TerraMaster U8-423 4.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | Q4_K_M | 1.5 GB | 12.5 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q2_K | 1.6 GB | 11.4 tok/s | Runs well |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q3_K_M | 1.5 GB | 12.0 tok/s | Runs well |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q2_K | 1.6 GB | 10.3 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | Q4_K_M | 1.6 GB | 11.1 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | Q3_K_M | 1.6 GB | 10.0 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q4_K_M | 1.6 GB | 10.3 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 2B | Q3_K_M | 2.0 GB | 6.8 tok/s | Slowtight fit |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q2_K | 1.6 GB | 10.5 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q4_K_M | 1.4 GB | 13.8 tok/s | Runs well |
Best Image models for the TerraMaster U8-423 4.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 1.6 GB | 71 s | SlowCPU offload |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 1.3 GB | 10.6 min | Very slowCPU offload |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 1.3 GB | 42 s | SlowCPU offload |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 1.3 GB | 10.6 min | Very slowCPU offload |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 1.3 GB | 10.6 min | Very slowCPU offload |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 1.3 GB | 2.2 min | SlowCPU offload |
Best Video models for the TerraMaster U8-423 4.0 GB
None of the video models in our catalog fit in this much memory.
Best Decision models for the TerraMaster U8-423 4.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | Jina Reranker v3.5 | Q8_0 | 1.6 GB | 17.2 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 1.6 GB | 17.2 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 7.6 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | Q8_0 | 1.7 GB | 12.7 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | Q8_0 | 1.6 GB | 17.2 s | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 8.7 s | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q5_K_M | 1.9 GB | 44.0 s | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | Q8_0 | 1.3 GB | 14.0 s | Very slow |
Other products with the Intel Celeron N5105 / N5095 NAS (4 GB)
AS6702TProduct page (opens in a new tab)
AS6704TProduct page (opens in a new tab)
AS6702T v2Product page (opens in a new tab)
AS6704T v2Product page (opens in a new tab)
FS6706TProduct page (opens in a new tab)
FS6712XProduct page (opens in a new tab)
AS5402TProduct page (opens in a new tab)
AS5404TProduct page (opens in a new tab)
MetaBox HS200 (HS200-PRO)Product page (opens in a new tab)
TS-464Product page (opens in a new tab)
TS-664Product page (opens in a new tab)
TS-364Product page (opens in a new tab)
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.