Модели

2 канонические LLM-модели от всех провайдеров

Показаны модели 1–2 из 2

Falcon-H1

ОАЭ

TII's hybrid Mamba-Transformer model that outperforms comparable offerings from Meta's Llama and Alibaba's Qwen in the 30-70B parameter range. Designed for real-world AI on everyday devices and resource-limited settings with state-of-the-art efficiency.

Контекст
131K
Добавлена
май 2026 г.

K2 Think

ОАЭ

A 32 billion parameter open-weights reasoning model by LLM360/MBZUAI, built on Qwen2.5-32B. Trained with reinforcement learning and verifiable rewards for long chain-of-thought reasoning, agentic planning, and complex problem solving in math, science, and code.

Контекст
131K
Добавлена
май 2026 г.