Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
https://huggingface.co/THUDM/GLM-Z1-9B-0414
GLM 4.6V Flash 9B model with vision, tools, and hybrid thinking enabled. using custom template to align it to ollama and the recomended sampling settigns by default. using unsloth quants at q4K_M
https://huggingface.co/zai-org/AutoGLM-Phone-9B
GLM-4.6V-Flash (9B) is a lightweight model optimized for local deployment and low-latency applications. It scales its context window to 128k tokens in training and achieves SoTA performance in visual understanding among models of similar parameter scales.
A finetuned version of GLM-Z1-9B-0414 trained on the Slipstream protocol - a semantic quantization system that achieves 82% token reduction in multi-agent AI communication. More info at: https://huggingface.co/collections/anthonym21/streamlined-inter-age
GLM-4-0414 series models.
GLM-4-Z1-9B-0414 9B小参数模型，其整体表现已处于同尺寸开源模型中的领先水平，此模型使用Ollama v0.6.6版本制作生成，需要Ollama v0.6.6及以上版本才能运行推理。
Base model
Biomedical evidence-based decision models (0.8B, 4B, 9B) built on Qwen3.5, with native Ollama `/v1/systemone` support for `choice`, `noul`, and `score`.
LongWriter-glm4-9b is trained based on glm-4-9b, and is capable of generating 10,000+ words at once.
HuatuoGPT-3-9B is a medical LLM built on Qwen3.5-9B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning. Q4_K_M Version.
Open-source distilled model based on Qwen3.5-9B.
Jev V2 Only Better its Bev, your drunk girlfriend: a decision model (Qwen3.5-9B base) trained to be confidently WRONG. 98% wrong, 96% sure. A joke, not advice.
The official ollama model for Gemma-2-9B-Chinese-Chat (https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat).
Gemma-SEA-LION-v3-9B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
Original model: bartowski/Gemma-2-9B-It-SPPO-Iter3-GGUF
Custom Qwen3.5 variants optimized for 128GB unified memory systems, such as AMD Ryzen AI Max+ 395. On Windows 11, GPU is limited to 96GB (32GB reserved for OS/CPU), requiring context window capped at 131072 tokens (128K) to fit within GPU memory limits.