Unlimited OCR 2 (3B-A0.6B) on Intel Celeron J4125 / J4105 NAS (8 GB)
Can the Intel Celeron J4125 / J4105 NAS (8 GB) run Unlimited OCR 2 (3B-A0.6B)?
Yes, it runs well
Runs well. At Q4_K_M it needs about 3.6 GB of 5.2 GB usable, with an estimated speed of 13.0 tok/s.
- Best quant
Q4_K_M- Generation speed
- 13.0 tok/s
- Prompt processing
- 16.7 tok/s
- First token (1K prompt)
- 61.4 s
- Largest safe context
- 34K
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 | 18.8 / 45 | |
|---|---|---|
| Memory fit | 25.0 / 25 | |
| Speed | 8.6 / 15 | |
| Memory use | 15.0 / 15 | |
| Match score | 67.4 / 100 |
Every quantization on the Intel Celeron J4125 / J4105 NAS (8 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 2.9 GB | 5.2 GB | 20.9 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 3.2 GB | 5.2 GB | 16.7 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q4_K_M | 3.6 GB | 5.2 GB | 13.0 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q5_K_M | 3.9 GB | 5.2 GB | 10.8 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q6_K | 4.3 GB | 5.2 GB | 9.2 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q8_0 | 5.1 GB | 5.2 GB | 6.8 tok/s | Slowtight fit | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
F16 | 8.2 GB | 5.2 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.
Other hardware that runs 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)
Quick answers
How much memory does Unlimited OCR 2 (3B-A0.6B) need on the Intel Celeron J4125 / J4105 NAS 8GB?
At Q4_K_M it needs about 3.6 GB. The Intel Celeron J4125 / J4105 NAS 8GB has 5.2 GB usable.
How fast is Unlimited OCR 2 (3B-A0.6B) on the Intel Celeron J4125 / J4105 NAS 8GB?
About 13.0 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.
Which quantization of Unlimited OCR 2 (3B-A0.6B) should I use on the Intel Celeron J4125 / J4105 NAS 8GB?
Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.
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.