Skip to content

Laguna S 2.1 on M5 Max 128 GB: VRAM, speed and fit

Laguna S 2.1 at 6-bit runs on the M5 Max 128 GB with 16K of context at about 46 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
123 GB
of 128 GB
Context
16K
auto
Speed
46 tok/s
Very fast
First reply
2.6 s
2K prompt

Where the memory goes

Model
89.8 GB
Context
840 MB
Overhead
548 MB
OS
32.0 GB
Free
4.9 GB
Memory
123 GB of 128 GB
Context
16K tokens · auto
Speed
46 tok/s · very fast
First reply
2.6 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated

What Laguna S 2.1 on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable91.1 GB neededPass
Headroom5% free4.9 GB free (5%)Pass
Context for chat16K or more16KPass
Writing speed15 tok/s or more46 tok/sPass
First replyunder 3 s, 2K prompt2.6 sPass

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 S 2.1
Parameters
118B, 8.4B active
Precision
6-bit (Q6_K)
Context
16K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Max 128 GB
GPU can use
96.0 GB of 128 GB

Worth trying

  • 8-bit cache: Room for 32K context

Running cost

At home
$2.63/mo
120 W at the wall
Renting instead
$131/mo
4× RTX A5000 at $1.08/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 poolside/Laguna-S-2.1-GGUF
vLLM
vllm serve poolside/Laguna-S-2.1
MLX (Mac)
mlx_lm.chat --model mlx-community/Laguna-S-2.1-oQ4e

Laguna S 2.1 on similar machines

All machines: Laguna S 2.1 VRAM requirements. Everything that runs here: what can the M5 Max 128 GB run?

Other models that run on M5 Max 128 GB

Questions

Can Laguna S 2.1 run on M5 Max 128 GB?

Laguna S 2.1 at 6-bit runs on the M5 Max 128 GB with 16K of context at about 46 tokens a second.

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