Skip to content
NEWSee what changed →

poolside · laguna

Laguna-XS.2

Laguna-XS.2 by poolside: a 33.4B-parameter mixture-of-experts open-weight model under the apache-2.0 license.

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

719,569 downloads · 320 likes · Model card · synced 2026-11-19

Specifications

Parameters
33.4B (1B active)
Architecture
moe · laguna
Layers
40
Hidden size
2,048
KV heads · head dim
8 · 128
Vocabulary
100,352
Native dtype
bfloat16
Context window
262,144 tokens
Released
2026-04-23
Last modified on Hub
2026-09-22

Features & licensing

License
apache-2.0
Commercial use
Yes
Modalities
text
Tool / function calling
No
Reasoning mode
No
Languages
EN
Quantised variants on Hub
AWQ, FP8, GGUF, bitsandbytes
Pipeline
text-generation
transformerssafetensorslagunatext-generationlaguna-xs.2vllmconversationalcustom_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-XS.2

Weights need about 73 GB at FP16, 39 GB at INT8 and 22 GB at INT4. The KV cache adds roughly 164 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 32.5 GB, which fits on 1 × NVIDIA A100 (80 GB).

GPU configurations at the reference workload
ConfigurationVRAMUtilisationEst. first tokenCloud / month
2 × NVIDIA L4 (24 GB)48 GB68 %~0.5 s$1,168
1 × NVIDIA L40S (48 GB)48 GB68 %~0.2 s$1,387
1 × NVIDIA A100 (80 GB)recommended80 GB41 %~0.1 s$2,336
1 × NVIDIA H100 (80 GB)80 GB41 %~0.0 s$3,285

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.