Laguna S 2.1 on M3 Ultra 256 GB: VRAM, speed and fit
Laguna S 2.1 at 8-bit runs on the M3 Ultra 256 GB with 1M of context at about 42 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 256 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 229 GB
- of 256 GB
- Context
- 1M
- auto
- Speed
- 42 tok/s
- 8.3 when full
- First reply
- 5.1 s
- 2K prompt
Where the memory goes
- Model
- 116 GB
- Context
- 48.1 GB
- Overhead
- 548 MB
- OS
- 64.0 GB
- Free
- 27.1 GB
- Memory
- 229 GB of 256 GB
- Context
- 1M tokens · auto
- Speed
- 42 tok/s · 8.3 when full
- First reply
- 5.1 s for a 2K prompt
- Running cost
- $3.55/mo at home · $287/mo on a cloud 4× A40
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 192 GB usable | 165 GB needed | Pass |
| Headroom | 5% free | 27.1 GB free (14%) | Pass |
| Context for chat | 16K or more | 1M | Pass |
| Writing speed | 15 tok/s or more | 42 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 5.1 s | Check |
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
- 8-bit (Q8_0)
- Context
- 1M, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 256 GB
- GPU can use
- 192 GB of 256 GB
Running cost
- At home
- $3.55/mo
- 162 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 22, 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- Model card
- huggingface.co/poolside/Laguna-S-2.1
Laguna S 2.1 on similar machines
- Mac mini M4 Pro 64 GBRuns
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 96 GBRuns
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBRuns
- Ryzen AI Max+ 395 128 GBRuns
All machines: Laguna S 2.1 VRAM requirements. Everything that runs here: what can the M3 Ultra 256 GB run?
Other models that run on M3 Ultra 256 GB
Questions
Can Laguna S 2.1 run on M3 Ultra 256 GB?
Laguna S 2.1 at 8-bit runs on the M3 Ultra 256 GB with 1M of context at about 42 tokens a second.
Report VR-0592N6Z, calculated Nov 22, 2026 from published specs, not benchmarked.