Skip to content

NVIDIA Nemotron 3 Nano 30B A3B BF16 on Mac mini M4 24 GB: VRAM, speed and fit

NVIDIA Nemotron 3 Nano 30B A3B BF16 at 3-bit runs on the M4 24 GB with 32K of context at about 44 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 24 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
23.2 GB
of 24.0 GB
Context
32K
auto
Speed
44 tok/s
Very fast
First reply
12 s
2K prompt

Where the memory goes

Model
14.4 GB
Context
239 MB
Overhead
596 MB
OS
8.0 GB
Free
830 MB
Memory
23.2 GB of 24.0 GB
Context
32K tokens · auto
Speed
44 tok/s · very fast
First reply
12 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What NVIDIA Nemotron 3 Nano 30B A3B BF16 on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable15.2 GB neededPass
Headroom5% free830 MB free (5%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more44 tok/sPass
First replyunder 3 s, 2K prompt12 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
NVIDIA Nemotron 3 Nano 30B A3B BF16
Parameters
31.6B, 3B active
Precision
3-bit (Q3_K_M)
Context
32K, 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 60K 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 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF
vLLM
vllm serve nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
MLX (Mac)
mlx_lm.chat --model mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-OptiQ-4bit

NVIDIA Nemotron 3 Nano 30B A3B BF16 on similar machines

Other models that run on Mac mini M4 24 GB

Questions

Can NVIDIA Nemotron 3 Nano 30B A3B BF16 run on Mac mini M4 24 GB?

NVIDIA Nemotron 3 Nano 30B A3B BF16 at 3-bit runs on the M4 24 GB with 32K of context at about 44 tokens a second.

Report VR-1SA5E76, calculated Nov 22, 2026 from published specs, not benchmarked.