Qwable-Ex
A personal experimental linear merge of strong Qwen3.5-9B lineage models focused on structured reasoning, agentic coding, and tool-use...
A personal experimental linear merge of strong Qwen3.5-9B lineage models focused on structured reasoning, agentic coding, and tool-use...
Eduardo-27B is a math tutor trained with multi-turn reinforcement learning. It was fine-tuned from Qwen/Qwen3.8-27B to teach a...
MIMESIS is a purpose-built user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral...
weighted/imatrix quants of https://huggingface.co/nightmedia/Qwen3.8-27B-Continuum For a convenient overview and download list, visit our model page for this model....
A 27B model that texts like a person and still does the work, in FP8 for 32 to...
A roleplay-focused LoRA finetune of Qwen3.5-4B-Uncensored, trained for immersive, descriptive, character-card style roleplay chat. Merged and quantized to...
> 新しい版(v2)があります:Qwen3.5-0.8B-Japanese-SFT-v2。 同じ言葉を止まらずに繰り返す問題(llama.cpp で 590回答中 8件 → 0件)と会話の自然さを改善し、日本語の一般常識も増えています。特に理由がなければ v2 を使ってください。 Qwen/Qwen3.5-0.8B を日本語向けに追加学習した、非公式の派生モデルです。Qwen チームとは関係ありません。 0.8B(8億パラメータ)と小さいので、GPU のないノートパソコンでも動きます(GGUF Q4KM で約 0.5...
Doosra is a cricket analytics app with a local AI copilot: you ask a question, and the model...
> New: Velocity with the Sharp chat template > at xhigh keeps its accuracy and thinks 14–26% less...
Original model: https://huggingface.co/OliviaRossi/MiMo-Ornith-9B-AGSI Model details: — Parameter count: 10B — Input support: text — Speculative decoding: yes (MTP)...