Skip to content

GPT Neox 20B on M3 Ultra 96 GB: VRAM, speed and fit

GPT Neox 20B at 8-bit runs on the M3 Ultra 96 GB with 2K of context at about 23 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 96 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
47.1 GB
of 96.0 GB
Context
2K
auto
Speed
23 tok/s
Fast
First reply
4.0 s
2K prompt

Where the memory goes

Model
20.5 GB
Context
2.1 GB
Overhead
547 MB
OS
24.0 GB
Free
48.9 GB
Memory
47.1 GB of 96.0 GB
Context
2K tokens · auto
Speed
23 tok/s · fast
First reply
4.0 s for a 2K prompt
Running cost
$3.55/mo at home · $33/mo on a cloud RTX A5000

Validation: Validated with conditions

What GPT Neox 20B on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable23.1 GB neededPass
Headroom5% free48.9 GB free (68%)Pass
Context for chat2K or more2KPass
Writing speed15 tok/s or more23 tok/sPass
First replyunder 3 s, 2K prompt4.0 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
GPT Neox 20B
Parameters
20.7B
Precision
8-bit (Q8_0)
Context
2K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 96 GB
GPU can use
72.0 GB of 96.0 GB

Running cost

At home
$3.55/mo
162 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/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 M3 Ultra 96 GB run?

Other models that run on M3 Ultra 96 GB

Questions

Can GPT Neox 20B run on M3 Ultra 96 GB?

GPT Neox 20B at 8-bit runs on the M3 Ultra 96 GB with 2K of context at about 23 tokens a second.

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