Skip to content

gpt-oss 20B on Mac mini M4 Pro 64 GB: VRAM, speed and fit

gpt-oss 20B at MXFP4 runs on the M4 Pro 64 GB with 128K of context at about 67 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 Pro 64 GB · MXFP4 · Ollama / LM Studio · Chat

GPU memory
31.0 GB
of 64.0 GB
Context
128K
auto
Speed
67 tok/s
34 when full
First reply
5.8 s
2K prompt

Where the memory goes

Model
11.3 GB
Context
3.0 GB
Overhead
739 MB
OS
16.0 GB
Free
33.0 GB
Memory
31.0 GB of 64.0 GB
Context
128K tokens · auto
Speed
67 tok/s · 34 when full
First reply
5.8 s for a 2K prompt
Running cost
$1.84/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated with conditions

What gpt-oss 20B on Mac mini M4 Pro 64 GB was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable15.0 GB neededPass
Headroom5% free33.0 GB free (69%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more67 tok/sPass
First replyunder 3 s, 2K prompt5.8 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-oss 20B
Parameters
20.9B, 3.6B active
Precision
MXFP4
Context
128K, 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
$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

Ollama
ollama run gpt-oss:20b
llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF
vLLM
vllm serve openai/gpt-oss-20b
MLX (Mac)
mlx_lm.chat --model mlx-community/gpt-oss-20b-MXFP4-Q4

gpt-oss 20B on similar machines

All machines: gpt-oss 20B 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 gpt-oss 20B run on Mac mini M4 Pro 64 GB?

gpt-oss 20B at MXFP4 runs on the M4 Pro 64 GB with 128K of context at about 67 tokens a second.

Report VR-0OSOIQ1, calculated Nov 22, 2026 from published specs, not benchmarked.