Qwen3.6-35B-A3B-GLM5.1-Claude4.7-Reasoning-Distilled
A dual-teacher distilled variant of Qwen3.6-35B-A3B that combines reasoning behaviors from both GLM-5.1 (754B MoE, SOTA on agentic/coding)...
A dual-teacher distilled variant of Qwen3.6-35B-A3B that combines reasoning behaviors from both GLM-5.1 (754B MoE, SOTA on agentic/coding)...
This model was converted to GGUF format from lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
BAR (Branch-Adapt-Route) is a modular post-training approach that extends a fully post-trained language model with new domain capabilities...
BAR (Branch-Adapt-Route) is a modular post-training approach that extends a fully post-trained language model with new domain capabilities...
This is a my second attempt on this model, which I hope to use as a local coder...
иматрично-калиброванные квантования GGUF MiniMaxAI/MiniMax-M2.7 — первая модель в линейке MiniMax, участвующая в собственной эволюции обучения. M2.7 соответствует или...
> Заменено. Это репозиторий является исследовательским артефактом из более ранней линии Outlier и больше не является рекомендуемой загрузкой....
This is a uncensored, full deep thinking Ernie 21B-A3B (MOE, 64 experts) fine tune using Claude 4.5 High...
Premium FP8 quantization with 1,024-sample calibration across 4 diverse datasets This is a premium FP8 quantized version of...
🚀 Первая реализация технологии разгрузки процессора MoE 🎯 99,9% Сокращение VRAM (2 МБ по сравнению с ожидаемым 15...