Kimi-K3.1-Pro-DSpark
LithosAI · draft model for lossless speculative decoding with Kimi-K3.1-Pro A DSpark draft head. In each decode step...
LithosAI · draft model for lossless speculative decoding with Kimi-K3.1-Pro A DSpark draft head. In each decode step...
27-миллиардная Qwen, у которой вырезан «лишний» кусок словаря, и две сборки квантования: IQ3XXS — целиком в 12 ГБ...
Русско-английская, кодоориентированная Gemma-4-E4B, у которой вырезан «лишний» кусок словаря. Не дистилляция, не файнтюн, не abliteration — веса модели...
Закрытые адаптеры LoRA, которые превращают петлевую модель Nanbeige4.2-3B (22 слоя × 2 петли) в диффузионный драйвер без потерь,...
A DFlash2 draft model fine-tuned for one target: DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF (IQ3S). It starts from incoai/Qwen3.8-Flash-Next-DFlash2`, which was trained on...
A ready-to-run .basalt pack for the Basalt inference engine (a fork of Strata, MIT). This is an uncensored...
This repository contains the DCOCO (DFlash Contextual Corrector) speculative-decoding drafter for NVIDIA Nemotron 3.5 Super VL 120B-A12B, from...
> [!CAUTION] > Research artifact. Safety alignment has been deliberately removed in the source model > (akumaburn/Swift-1.5-Qwen3.8-27b-heretic). >...
Quantized, Abliterated, and fitted by LexiPanel. Its Fit planner chose the tensor mix to fill one 24 GB...
Research project for inference of large dense models on the M6 Apple Neural Engine. ANEMLL Forge shares quantization,...