Unlimited OCR 2 (3B-A0.6B) on Intel Atom C3538 / C3558 NAS (4 GB)
Can the Intel Atom C3538 / C3558 NAS (4 GB) run Unlimited OCR 2 (3B-A0.6B)?
No, it doesn’t fit
No. Unlimited OCR 2 (3B-A0.6B) needs about 2.6 GB even at Q2_K; the Intel Atom C3538 / C3558 NAS (4 GB) has 2.0 GB usable.
Download Unlimited OCR 2 (3B-A0.6B)
Original weights · Hugging Face
Full-precision files from Baidu, for fine-tuning, vLLM, Transformers.
Official repo · GitHub
Reference code, inference scripts and docs from Baidu. The weights themselves download from Hugging Face.
github.com/baidu/Unlimited-OCR (opens in a new tab)
git clone https://github.com/baidu/Unlimited-OCRHow it’s rated
Match score
To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.
| Model quality | 4.2 / 45 | |
|---|---|---|
| Memory fit | 0.0 / 25 | |
| Speed | 0.0 / 15 | |
| Memory use | 0.0 / 15 | |
| Match score | 4.2 / 100 |
Every quantization on the Intel Atom C3538 / C3558 NAS (4 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 2.6 GB | 2.0 GB | — | Won't run | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 2.9 GB | 2.0 GB | — | Won't run | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q4_K_M | 3.3 GB | 2.0 GB | — | Won't run | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q5_K_M | 3.6 GB | 2.0 GB | — | Won't run | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q6_K | 4.0 GB | 2.0 GB | — | Won't run | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q8_0 | 4.8 GB | 2.0 GB | — | Won't run | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
F16 | 7.9 GB | 2.0 GB | — | Won't run | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Original weights (opens in a new tab) |
Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.
Hardware that can run it
-
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
Apple M4 (16 GB)
-
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
Intel Arc B580
-
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 3060 12GB
-
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4070 SUPER
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4060
-
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.
Apple M4 (24 GB)
Models that do run on the Intel Atom C3538 / C3558 NAS (4 GB)
- 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B
- 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B
- 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B
- 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B
- 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B
Quick answers
How much memory does Unlimited OCR 2 (3B-A0.6B) need on the Intel Atom C3538 / C3558 NAS 4GB?
Even at Q2_K it needs about 2.6 GB; the Intel Atom C3538 / C3558 NAS 4GB has 2.0 GB usable.
What can the Intel Atom C3538 / C3558 NAS 4GB run instead?
LFM3 1.7B, PaddleOCR-VL 1.6 0.9B and LFM3-VL 2B run best on it; the page lists more, each with its speed.
What hardware can run Unlimited OCR 2 (3B-A0.6B)?
M4 16GB, Arc B580 12GB and RTX 3060 12GB run it; the page lists more, each with its speed.
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.