Skip to content

Olmo 3.1 32B on Mac mini M4 Pro 64 GB: VRAM, speed and fit

Olmo 3.1 32B at 8-bit runs on the M4 Pro 64 GB with 64K of context at about 6.4 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 Pro 64 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
53.2 GB
of 64.0 GB
Context
64K
auto
Speed
6.4 tok/s
Reading speed
First reply
22 s
2K prompt

Where the memory goes

Model
31.9 GB
Context
4.8 GB
Overhead
612 MB
OS
16.0 GB
Free
10.8 GB
Memory
53.2 GB of 64.0 GB
Context
64K tokens · auto
Speed
6.4 tok/s · reading speed
First reply
22 s for a 2K prompt
Running cost
$1.84/mo at home · $61/mo on a cloud 2× RTX A4500

Validation: Not validated

What Olmo 3.1 32B on Mac mini M4 Pro 64 GB was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable37.2 GB neededPass
Headroom5% free10.8 GB free (22%)Pass
Context for chat16K or more64KPass
Writing speed15 tok/s or more6.4 tok/sCheck
First replyunder 3 s, 2K prompt22 sFails

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
Olmo 3.1 32B
Parameters
32.2B
Precision
8-bit (Q8_0)
Context
64K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 Pro 64 GB
GPU can use
48.0 GB of 64.0 GB

Running cost

At home
$1.84/mo
84 W at the wall
Renting instead
$61/mo
2× RTX A4500 at $0.50/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run olmo-3.1:32b-instruct
llama.cpp
llama-server -hf unsloth/Olmo-3.1-32B-Instruct-GGUF
vLLM
vllm serve allenai/Olmo-3.1-32B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Olmo-3.1-32B-Instruct-4bit

Olmo 3.1 32B on similar machines

All machines: Olmo 3.1 32B VRAM requirements. Everything that runs here: what can the Mac mini M4 Pro 64 GB run?

Other models that run on Mac mini M4 Pro 64 GB

Questions

Can Olmo 3.1 32B run on Mac mini M4 Pro 64 GB?

Olmo 3.1 32B at 8-bit runs on the M4 Pro 64 GB with 64K of context at about 6.4 tokens a second.

Report VR-0NYW47L, calculated Nov 22, 2026 from published specs, not benchmarked.