Skip to content
NEWSee what changed →

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.

apache-2.0Mixture of experts262K contextAuto-imported · not yet reviewed

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
vllmsafetensorslagunalaguna-m.1sglangbf16moetext-generationconversationalcustom_codeeval-results

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).

GPU configurations at the reference workload
ConfigurationVRAMUtilisationEst. first tokenCloud / month
6 × NVIDIA L40S (48 GB)288 GB86 %~0.2 s$8,322
4 × NVIDIA A100 (80 GB)recommended320 GB78 %~0.1 s$9,344
4 × NVIDIA H100 (80 GB)320 GB78 %~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.