Hy3-REAP-200B-21B
A 33%-expert-pruned version of Tencent Hunyuan Hy3 (295B / A21B), compressed with REAP (Router-weighted Expert Activation Pruning) —...
Метка: hunyuan
Hy3-colibri-int4
Pre-converted weights for colibrì — a pure-C engine that runs huge MoE models on consumer hardware by keeping...
SuperHY3-abliterated-MLX-4bit
The high-memory Apple Silicon edition of SuperHY3, with the same fused OBLITERATUS and SuperTune behavior as the NVFP4...
Hy3-JANG_2K-MTP
Quantized tencent/Hy3 for Apple Silicon MLX / JANG runtimes — a 295B-total / 21B-active text MoE, packed to...
Hy3-AWQ-INT4
Version 26.05.01 Calibration STEM and Agentic Languages EN ZH HI AR RU JA KO NL FR ES Model...
Hy3-GGUF
High-quality imatrix GGUF quantizations of tencent/Hy3, Tencent’s 295B-parameter Mixture-of-Experts model with ~21B active parameters per token. Produced with...
Hy3-REAP75-MLX-4bit
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Hunyuan-A13B-Instruct-4bit
This model mlx-community/Hunyuan-A13B-Instruct-4bit was converted to MLX format from tencent/Hunyuan-A13B-Instruct using mlx-lm version 0.25.3. Модальности:Генерация текста Области применения:Диалог...
hy3-w4a16-mtp
> Выпущено 16 июля 2026 г. Все этапы пройдены: проверка артефакта (—check-mtp), > качество по сравнению с FP8...
Hy3-REAP-48e
Экспертно-обрезанная версия tencent/Hy3, созданная с помощью REAP (экспертная обрезка активации с учетом маршрутизатора). 192 маршрутизируемых эксперта каждого уровня...