Skip to content

GPT Neox 20B on Mac mini M4 32 GB: VRAM, speed and fit

GPT Neox 20B at 6-bit runs on the M4 32 GB with 2K of context at about 5.8 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
29.1 GB
of 32.0 GB
Context
2K
auto
Speed
5.8 tok/s
Slow
First reply
28 s
2K prompt

Where the memory goes

Model
15.8 GB
Context
2.1 GB
Overhead
547 MB
OS
10.7 GB
Free
2.9 GB
Memory
29.1 GB of 32.0 GB
Context
2K tokens · auto
Speed
5.8 tok/s · slow
First reply
28 s for a 2K prompt
Running cost
$0.85/mo at home · $30/mo on a cloud RTX A4500

Validation: Not validated

What GPT Neox 20B on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable18.4 GB neededPass
Headroom5% free2.9 GB free (14%)Pass
Context for chat2K or more2KPass
Writing speed15 tok/s or more5.8 tok/sFails
First replyunder 3 s, 2K prompt28 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
GPT Neox 20B
Parameters
20.7B
Precision
6-bit (Q6_K)
Context
2K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 32 GB
GPU can use
21.3 GB of 32.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$30/mo
RTX A4500 at $0.25/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 mradermacher/gpt-neox-20b-i1-GGUF
vLLM
vllm serve EleutherAI/gpt-neox-20b

GPT Neox 20B on similar machines

All machines: GPT Neox 20B VRAM requirements. Everything that runs here: what can the Mac mini M4 32 GB run?

Other models that run on Mac mini M4 32 GB

Questions

Can GPT Neox 20B run on Mac mini M4 32 GB?

GPT Neox 20B at 6-bit runs on the M4 32 GB with 2K of context at about 5.8 tokens a second.

Report VR-0N4V2BM, calculated Nov 22, 2026 from published specs, not benchmarked.