gemma · Ollama

The most accurate model in the family, and the best at telling lookalike intents apart. Define intents at prompt time, no retraining. It always returns the single best match, and refuses only if you add a catch-all intent.

1.5b

398 Pulls 1 Tag Updated 2 weeks ago

glm-5.3-flash

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

vision tools thinking cloud

136.3K Pulls 1 Tag Updated 2 weeks ago

ibm/granite4.2

IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, thinking and structured JSON output. Released under Apache 2.0 license.

3b 8b 30b

527 Pulls 48 Tags Updated 2 weeks ago

richards_michael/gemma3

vision 4b

9 Pulls 1 Tag Updated 3 weeks ago

mukunthpr/gemma4-e4b-code

vision tools thinking

141 Pulls 1 Tag Updated 3 weeks ago

23g110karthick/Zefra-V1-9B

ZEFRA-9B is a general-purpose AI model built for reasoning, coding, mathematics, knowledge, writing, problem-solving, and security-conscious assistance. It is designed to provide practical, reliable responses while protecting sensitive information and res

5 Pulls 1 Tag Updated 3 weeks ago