Parable-SmolLM3-3B-Claude-Fable-5
Часть серии «Притча»: небольшие местные магистры права, настроенные на подлинные следы агентов. Это HuggingFaceTB/SmolLM3-3B, настроенный на реальные транскрипты...
Часть серии «Притча»: небольшие местные магистры права, настроенные на подлинные следы агентов. Это HuggingFaceTB/SmolLM3-3B, настроенный на реальные транскрипты...
A 9–10 GB mixture-of-experts specialist derived from google/gemma-4-26B-A4B-it by pruning 25 % of routed experts with routing-aware REAP...
> 📢 V2.0 is available — We have released an updated model with enhanced tool-calling capabilities. Welcome to...
A 30.5B-parameter Mixture-of-Experts reasoning model built from Qwen3-30B-A3B through a single CoT-preserving BF16 LoRA pass. Satella is the...
> ~3 ГБ оперативной памяти — это все, что вам нужно. Ноутбук, старый графический процессор, коробки класса Raspberry-Pi-...
Mistral Code Architect 7B is a highly specialized, locally fine-tuned large language model designed for advanced software development,...
A high-efficiency FP8-quantized Mixture-of-Experts model fine-tuned and optimized for coding, software engineering, and agentic development workflows. It is...
The only Ornith MTP build that fits 24 GB cards. Ornith-1.0-35B (Q4KM) with the multi-token-prediction head from Qwen3.6-35B-A3B-MTP...
Qwen3.5-24.5B-Reapped-v1 is a model checkpoint packaged for compatible Hugging Face runtimes, published by groxaxo. It is intended for...
Code-Writer-V2-Obliterated-BF16 is a BF16 checkpoint preserving the model in a broadly supported training and inference format, published by...