Models

Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.

powered by glm-5.1

ollama run hf.co/huihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF:UD-IQ1_S

Reduced-refusal Muse Glimmer 30B via Heretic: 52/100 refusals (from 99), KL 0.063. Vision, Apache-2.0.

Gemma 4 E2B (Google DeepMind) with thinking mode disabled. Compact multimodal model — 2.3B effective / 5.1B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.

Gemma 4 E2B (Google DeepMind) with thinking mode enabled. Compact multimodal model — 2.3B effective / 5.1B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.

Built this model to fit RTX 5070 with 12GB of VRAM