Domyn-Edge-SFT
> [!IMPORTANT] > Phased release. Domyn Edge is a rolling release in three bundles. This checkpoint was >...
> [!IMPORTANT] > Phased release. Domyn Edge is a rolling release in three bundles. This checkpoint was >...
Nesi2 — это большая языковая модель без цензуры, разработанная и оптимизированная Nesilabs специально для наступательной и защитной кибербезопасности:...
UDGAM LABS · Tool-calling model, GGUF files · 384M parameters This repo holds the GGUF files of Udgam-384M-Chat...
GRAFT-10B-A2B is a ~10B-parameter mixture-of-experts chat model from UltraLabs. Only about 2B parameters are active per token, so...
Quantized GGUF builds of Aleph-Alpha/Kolibri-1 — Aleph Alpha’s 78.10B-parameter (3.46B active) German/English MoE reasoning model — converted from...
A 27B model that texts like a person and still does the work, in FP8 for 32 to...
Doosra is a cricket analytics app with a local AI copilot: you ask a question, and the model...
Qwen3Loop-0.6B-Tool-Calling-SFT — узкий специалист по вызову инструментов: рекуррентная архитектура Qwen3Loop с 0,6B-параметром, полностью настроенная на кураторскую учебную программу...
medismera/Qwen3.8-27B-OBLITERATED-Mythos-Class-Agentic is a production-engineered configuration, tokenizer, and reasoning upgrade for Qwen3.8-27B-OBLITERATED. It resolves the critical function-calling, chat template...
4-bit quantized MLX format of ibm-granite/granite-4.2-8b optimized for Apple Silicon inference. — 4-bit Quantization: Low memory footprint (~4.9...