Skip to content

Llama 3.1 8B on Mac mini M4 24 GB: VRAM, speed and fit

Llama 3.1 8B at 8-bit runs on the M4 24 GB with 52K of context at about 12 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
23.1 GB
of 24.0 GB
Context
52K
auto
Speed
12 tok/s
6.5 when full
First reply
9.9 s
2K prompt

Where the memory goes

Model
7.9 GB
Context
6.5 GB
Overhead
635 MB
OS
8.0 GB
Free
957 MB
Memory
23.1 GB of 24.0 GB
Context
52K tokens · auto
Speed
12 tok/s · 6.5 when full
First reply
9.9 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What Llama 3.1 8B on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable15.1 GB neededPass
Headroom5% free957 MB free (6%)Pass
Context for chat16K or more52KPass
Writing speed15 tok/s or more12 tok/sCheck
First replyunder 3 s, 2K prompt9.9 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
Llama 3.1 8B
Parameters
8B
Precision
8-bit (Q8_0)
Context
52K, 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 96K 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

Ollama
ollama run llama3.1:8b
llama.cpp
llama-server -hf unsloth/Llama-3.1-8B-Instruct-GGUF
vLLM
vllm serve meta-llama/Llama-3.1-8B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Llama-3.1-8B-Instruct-4bit

Llama 3.1 8B on similar machines

All machines: Llama 3.1 8B 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 Llama 3.1 8B run on Mac mini M4 24 GB?

Llama 3.1 8B at 8-bit runs on the M4 24 GB with 52K of context at about 12 tokens a second.

Report VR-0KY96VU, calculated Nov 22, 2026 from published specs, not benchmarked.