Skip to content

Phi 3.5 Mini Instruct on Mac mini M4 24 GB: VRAM, speed and fit

Phi 3.5 Mini Instruct at 8-bit runs on the M4 24 GB with 28K of context at about 23 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 24 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
22.7 GB
of 24.0 GB
Context
28K
auto
Speed
23 tok/s
6.4 when full
First reply
5.2 s
2K prompt

Where the memory goes

Model
3.8 GB
Context
10.5 GB
Overhead
415 MB
OS
8.0 GB
Free
1.3 GB
Memory
22.7 GB of 24.0 GB
Context
28K tokens · auto
Speed
23 tok/s · 6.4 when full
First reply
5.2 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 Phi 3.5 Mini Instruct on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable14.7 GB neededPass
Headroom5% free1.3 GB free (8%)Pass
Context for chat16K or more28KPass
Writing speed15 tok/s or more23 tok/sPass
First replyunder 3 s, 2K prompt5.2 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
Phi 3.5 Mini Instruct
Parameters
3.8B
Precision
8-bit (Q8_0)
Context
28K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 24 GB
GPU can use
16.0 GB of 24.0 GB

Worth trying

  • 8-bit cache: Room for 52K context

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 22, 2026.

How to run it

llama.cpp
llama-server -hf bartowski/Phi-3.5-mini-instruct-GGUF
vLLM
vllm serve microsoft/Phi-3.5-mini-instruct

Phi 3.5 Mini Instruct on similar machines

All machines: Phi 3.5 Mini Instruct VRAM requirements. Everything that runs here: what can the Mac mini M4 24 GB run?

Other models that run on Mac mini M4 24 GB

Questions

Can Phi 3.5 Mini Instruct run on Mac mini M4 24 GB?

Phi 3.5 Mini Instruct at 8-bit runs on the M4 24 GB with 28K of context at about 23 tokens a second.

Report VR-1392H6E, calculated Nov 22, 2026 from published specs, not benchmarked.