Version 26.05.01 Calibration STEM and Agentic Languages EN ZH HI AR RU JA KO NL FR ES Model Size 76.83 GB Contact Email Benchmarks as of 21 July 2026. Laguna S 2.1 in bold; a dash (-) marks a benchmark a model was not evaluated on. Scores marked * are as reported by third parties: Terminal-Bench 2.1 and DeepSWE via Artificial Analysis, SWE Atlas via Scale AI’s official leaderboard, and Toolathlon Verified via its official leaderboard. Full evaluation trajectories: trajectories.poolside.ai. Laguna S 2.1 uses the same laguna architecture as Laguna XS 2.1, so the same engine integrations apply (vLLM, SGLang, Transformers, TRT-LLM, llama.cpp). At 118B parameters the BF16 checkpoint needs multiple GPUs (roughly 236GB of weights); quantized variants reduce this substantially. > [!NOTE] > Optional: speculative decoding with DFlash. Pair with the > Laguna S 2.1 DFlash draft model > by adding > —speculative-config ‘{«model»:»poolside/Laguna-S-2.1-DFlash»,»numspeculativetokens»:7,»method»:»dflash»}’. Note the flag names differ from vLLM’s (—toolparser, and the reasoning parser is laguna, not poolsidev1). GGUF conversions are available at poolside/Laguna-S-2.1-GGUF. Serve with…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: cyankiwi
Теги: laguna, laguna-s-2.1, vllm, conversational, custom_code, compressed-tensors
Лайков: 4 | Загрузок: 8,557
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
