Skip to content

Laguna XS 2.1 on Mac mini M4 32 GB: VRAM, speed and fit

Laguna XS 2.1 at 4-bit runs on the M4 32 GB with 20K of context at about 41 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat

GPU memory
30.9 GB
of 32.0 GB
Context
20K
auto
Speed
41 tok/s
30 when full
First reply
12 s
2K prompt

Where the memory goes

Model
18.9 GB
Context
860 MB
Overhead
516 MB
OS
10.7 GB
Free
1.1 GB
Memory
30.9 GB of 32.0 GB
Context
20K tokens · auto
Speed
41 tok/s · 30 when full
First reply
12 s for a 2K prompt
Running cost
$0.85/mo at home · $33/mo on a cloud RTX A5000

Validation: Not validated

What Laguna XS 2.1 on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable20.2 GB neededPass
Headroom5% free1.1 GB free (5%)Pass
Context for chat16K or more20KPass
Writing speed15 tok/s or more41 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
Laguna XS 2.1
Parameters
33.4B, 3B active
Precision
4-bit (Q4_K_M)
Context
20K, 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

Worth trying

  • 8-bit cache: Room for 40K context

Running cost

At home
$0.85/mo
39 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 mudler/Laguna-XS-2.1-APEX-GGUF
vLLM
vllm serve poolside/Laguna-XS-2.1
MLX (Mac)
mlx_lm.chat --model mlx-community/Laguna-XS-2.1-4bit

Laguna XS 2.1 on similar machines

All machines: Laguna XS 2.1 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 Laguna XS 2.1 run on Mac mini M4 32 GB?

Laguna XS 2.1 at 4-bit runs on the M4 32 GB with 20K of context at about 41 tokens a second.

Report VR-1SOEYO6, calculated Nov 22, 2026 from published specs, not benchmarked.