Kimi-K2.5-P48NVFP4-MoESQ
A W4A4 + paired-4:8 sparse compressed checkpoint of moonshotai/Kimi-K2.5, produced with MoESQ. The MoE expert weights are NVFP4...
A W4A4 + paired-4:8 sparse compressed checkpoint of moonshotai/Kimi-K2.5, produced with MoESQ. The MoE expert weights are NVFP4...
Myosotis-1.5-base is the second flagship release from us, built on the FWKV architecture. Myosotis-1.5 is engineered to never...
PPCM is a ~9M three-layer encoder (CCEL → CTIL → CPRL) over Top-7 candidates. It ranks causally consistent...
A DSpark speculator for the Inkling NVFP4 target, enabling faster inference through speculative decoding. DSpark extends the DFlash...
Этот репозиторий содержит черновую модель DFlash для думающих машин/Inkling-NVFP4. Это не самостоятельная языковая модель. Он предназначен для сопряжения...
This is a block-size-16 Domino draft model for the target model Qwen/Qwen3.6-27B. It is intended for speculative decoding...
A DFlash speculative-decoding drafter for Qwen/Qwen3.6-35B-A3B and its derivatives — including Ornith-1.0-35B-AEON-Ultimate-Uncensored (a light RL post-train of that...
Эта черновая модель DFlash является совместной переподготовкой Z-Lab и Modal, обученной с длиной последовательности 40K и вниманием скользящего...
This is a fork of https://huggingface.co/z-lab/Qwen3.6-27B-DFlash This model is still under training, and inference engine support may not...
This model was converted to FP16 from z-lab/Qwen3.6-35B-A3B-DFlash BF16. >DFlash is a novel speculative decoding method that utilizes...