Laguna-XS-2.1-3bit
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Метка: laguna
Laguna-XS-2.1-MLX-5bit
Laguna XS 2.1, self-quantized to MLX by Atomic Chat. Built straight from Poolside’s original weights with a per-tensor...
Laguna-S-2.1-AWQ-INT4
Version 26.05.01 Calibration STEM and Agentic Languages EN ZH HI AR RU JA KO NL FR ES Model...
Laguna-S-2.1-oQ5e
Calibrated 5-bit MLX quantization of poolside/Laguna-S-2.1 (118B total, 8B activated per token), produced with oMLX oQ at level...
Laguna-S-2.1-oQ3e
Calibrated 3-bit MLX quantization of poolside/Laguna-S-2.1 (118B total, 8B activated per token), produced with oMLX oQ at level...
Laguna-S-2.1-MLX-4bit
MLX 4-bit affine quantization of poolside/Laguna-S-2.1, packaged for Apple Silicon experiments and local OpenAI-compatible serving. Laguna S 2.1...
Laguna-XS-2.1-4bit
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Laguna-XS.2-GGUF
First-ever GGUF conversion of poolside/Laguna-XS.2, produced as part of the Poolside Research Hackathon. Laguna XS.2 is a 33.4B...
Laguna-XS.2-4bit
Эта модель mlx-community/Laguna-XS.2-4bit была преобразована в формат MLX из poolside/Laguna-XS.2 с использованием mlx-lm версии 0.31.3. Модальности:Генерация текста Области...
Laguna-XS-2.1-CRACK-GGUF
Компактная модель кодирования Laguna MoE · llama.cpp GGUF · Q6K · Q4KM · Q2K Отказ удален с сохранением...