Skip to content

Laguna M.1 on DGX Spark: VRAM, speed and fit

Laguna M.1 at 3-bit runs on the DGX Spark 128 GB with 36K of context at about 16 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
121 GB
of 128 GB
Context
36K
auto
Speed
16 tok/s
8.4 when full
First reply
5.3 s
2K prompt

Where the memory goes

Model
103 GB
Context
9.8 GB
Overhead
580 MB
OS
7.7 GB
Free
7.1 GB
Memory
121 GB of 128 GB
Context
36K tokens · auto
Speed
16 tok/s · 8.4 when full
First reply
5.3 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Validated with conditions

What Laguna M.1 on DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory120 GB usable113 GB neededPass
Headroom5% free7.1 GB free (6%)Pass
Context for chat16K or more36KPass
Writing speed15 tok/s or more16 tok/sPass
First replyunder 3 s, 2K prompt5.3 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
Laguna M.1
Parameters
226B, 23.5B active
Precision
3-bit (Q3_K_M)
Context
36K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Spark 128 GB
GPU can use
120 GB of 128 GB

Worth trying

  • 8-bit cache: Room for 72K context

Running cost

At home
$3.15/mo
144 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/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 sigargv/Laguna-M.1-GGUF
vLLM
vllm serve poolside/Laguna-M.1
MLX (Mac)
mlx_lm.chat --model mlx-community/Laguna-M.1-4bit

Laguna M.1 on similar machines

All machines: Laguna M.1 VRAM requirements. Everything that runs here: what can the DGX Spark run?

Other models that run on DGX Spark

Questions

Can Laguna M.1 run on DGX Spark?

Laguna M.1 at 3-bit runs on the DGX Spark 128 GB with 36K of context at about 16 tokens a second.

Report VR-06TFHX9, calculated Nov 22, 2026 from published specs, not benchmarked.