Carnice-27b-MLX-oQ8
This repo is a straight MLX oQ8 quant of kai-os/Carnice-27b for local Apple Silicon inference. No other edits,...
This repo is a straight MLX oQ8 quant of kai-os/Carnice-27b for local Apple Silicon inference. No other edits,...
This checkpoint preserves the hybrid Qwen3.5 DeltaNet + softmax architecture and MTP (Multi-Token Prediction) head from the BF16...
For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available...
> [!IMPORTANT] > Naming notice (2026-04-10). The «HLWQ» technique used in this model is being rebranded to HLWQ...
This model is a fine-tuned version of Qwen/Qwen3.5-9B on the godzillaxz/polymarket-trading-data dataset. The following hyperparameters were used during...
This model was converted to MLX format from Qwen/Qwen3.5-27B using oMLX v0.2.24 with oQ Quantization. — Level: oQ4...
> Обновление: > Эта модель была дополнительно улучшена дополнительными данными рассуждений, полученными из Qwen3.5-27B. > > Новые данные...
PocketPlaning-1 — это специализированная модель планирования агента ИИ, построенная на Qwen3.5-27B. Он точно настроен для интеллектуальной маршрутизации задач,...
This model is a fine-tuned version of Qwen/Qwen3.5-4B, specialized for emotion recognition and emotionally-aware text generation. We provide...
figured out what was wrong. config. json had an extra usecache: false. so now after a proper run...