awal-gpt-v0.2-7b
AWAL GPT v0.2 is an open-source Large Language Model fine-tuned for the Amazigh (Tamazight) language, with a primary...
AWAL GPT v0.2 is an open-source Large Language Model fine-tuned for the Amazigh (Tamazight) language, with a primary...
This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-4B for use with mlx-vlm speculative decoding....
This repository contains Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.6-27B for use with mlx-vlm speculative decoding. This...
Supertron2.1-0.6B-GGUF содержит экспорт GGUF Surpem/Supertron2.1-0.6B, компактной универсальной модели на основе Qwen3 от Surpem. Этот репозиторий предназначен для локального...
Квантования GGUF z-лабораторной модели DFlash для Gemma 4 26B A4B. Используйте с BeeLlama.cpp, форком llama.cpp с расширенными функциями...
Fine-tune em português (PT-BR) do modelo base Qwen3.5-4B, treinado via SFT (Supervised Fine-Tuning) para melhorar a fluência e...
Part of the CoNDeNse project — compressing the reasoning capability of large models into small, deployable ones. —...
MXFP4MOE** GGUF quantization of Qwen3.6-35B-A3B, Alibaba Cloud’s efficient 35B MoE multimodal foundation model (3B activated) with 262K context,...
NVFP4 GGUF quantization of Qwen3.5-4B, Alibaba Cloud’s compact 4B multimodal foundation model with 262K context, 201 languages, and...
distill-1.7B is a domain-specific Expert Language Model — not a general-purpose chatbot. It does exactly one thing: compress...