poolside · laguna
Laguna-M.1
Laguna-M.1 by poolside: a 225.8B-parameter mixture-of-experts open-weight model under the apache-2.0 license.
677,802 downloads · 150 likes · Model card · synced 2026-11-19
Specifications
- Parameters
- 225.8B (14.1B active)
- Architecture
- moe · laguna
- Layers
- 70
- Hidden size
- 4,096
- KV heads · head dim
- 8 · 128
- Vocabulary
- 100,352
- Native dtype
- bfloat16
- Context window
- 262,144 tokens
- Released
- 2026-06-15
- Last modified on Hub
- 2026-07-14
Features & licensing
- License
- apache-2.0
- Commercial use
- Yes
- Modalities
- text
- Tool / function calling
- No
- Reasoning mode
- No
- Languages
- EN
- Quantised variants on Hub
- FP8, GGUF, bitsandbytes
- Pipeline
- text-generation
Task fit
Editorial scores (0–100) used by the recommendation engine.
- Chat70
- RAG / Q&A70
- Code70
- Summarisation70
- Extraction70
- Agents70
Hardware to run Laguna-M.1
Weights need about 497 GB at FP16, 261 GB at INT8 and 149 GB at INT4. The KV cache adds roughly 287 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 248.2 GB, which fits on 4 × NVIDIA A100 (80 GB).
| Configuration | VRAM | Utilisation | Est. first token | Cloud / month |
|---|---|---|---|---|
| 6 × NVIDIA L40S (48 GB) | 288 GB | 86 % | ~0.2 s | $8,322 |
| 4 × NVIDIA A100 (80 GB)recommended | 320 GB | 78 % | ~0.1 s | $9,344 |
| 4 × NVIDIA H100 (80 GB) | 320 GB | 78 % | ~0.0 s | $13,140 |
Estimates only. Run an assessment for your own traffic.
Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.