Skip to content

Unlimited OCR 2 on Mac mini M4 16 GB: VRAM, speed and fit

Unlimited OCR 2 at 8-bit runs on the M4 16 GB with 104K of context at about 71 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 16 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
15.3 GB
of 16.0 GB
Context
104K
auto
Speed
71 tok/s
12 when full
First reply
3.9 s
2K prompt

Where the memory goes

Model
3.3 GB
Context
6.1 GB
Overhead
549 MB
OS
5.3 GB
Free
746 MB
Memory
15.3 GB of 16.0 GB
Context
104K tokens · auto
Speed
71 tok/s · 12 when full
First reply
3.9 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated with conditions

What Unlimited OCR 2 on Mac mini M4 16 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.7 GB usable9.9 GB neededPass
Headroom5% free746 MB free (7%)Pass
Context for chat16K or more104KPass
Writing speed15 tok/s or more71 tok/sPass
First replyunder 3 s, 2K prompt3.9 sCheck

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Unlimited OCR 2
Parameters
3.3B, 1.1B active
Precision
8-bit (Q8_0)
Context
104K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 16 GB
GPU can use
10.7 GB of 16.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf AtomicChat/Unlimited-OCR-2-GGUF
vLLM
vllm serve baidu/Unlimited-OCR-2
MLX (Mac)
mlx_lm.chat --model mlx-community/Unlimited-OCR-2-8bit

Unlimited OCR 2 on similar machines

All machines: Unlimited OCR 2 VRAM requirements. Everything that runs here: what can the Mac mini M4 16 GB run?

Other models that run on Mac mini M4 16 GB

Questions

Can Unlimited OCR 2 run on Mac mini M4 16 GB?

Unlimited OCR 2 at 8-bit runs on the M4 16 GB with 104K of context at about 71 tokens a second.

Report VR-19XPV2T, calculated Nov 22, 2026 from published specs, not benchmarked.