130 Pulls 1 Tag Updated 5 days ago
Gemma 4 31B dense, vision + native tool calling.
39 Pulls 1 Tag Updated 1 week ago
2,515 Pulls 5 Tags Updated 1 month ago
Gemma 4 31B (Google DeepMind) with thinking mode enabled. Best for complex reasoning, math, coding, and multi-step analysis. Knowledge cutoff: January 2025. Sampling: temperature 1.0 / top_p 0.95 / top_k 64.
390 Pulls 1 Tag Updated 1 month ago
Gemma 4 31B (Google DeepMind) with thinking mode disabled. Best for quick questions, chat, and straightforward tasks. Knowledge cutoff: January 2025. Sampling: temperature 1.0 / top_p 0.95 / top_k 64.
348 Pulls 1 Tag Updated 1 month ago
PhineGPT is a custom AI assistant model built on top of Gemma4 31B using Ollama. It is designed as a general-purpose assistant optimized for accuracy, structured reasoning, and developer-friendly output.
45 Pulls 1 Tag Updated 1 month ago
A Gemma 3 1B model optimized for android devices
149 Pulls 2 Tags Updated 1 year ago
llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF
950 Pulls 1 Tag Updated 4 days ago
From DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-Instruct-GGUF:Q6_K
575 Pulls 1 Tag Updated 2 weeks ago
336 Pulls 1 Tag Updated 1 week ago
5,176 Pulls 1 Tag Updated 1 month ago
These are essentially Completely UNCENSORED versions of GEMMA3 1B and 4B. Just NJOY!!!
6,472 Pulls 2 Tags Updated 4 months ago
Supera a modelos de 97B como Qwen3.5 - Multimodal Vision / Audio, Razonamiento (uso comercial valido) sin censura
1,359 Pulls 1 Tag Updated 1 month ago
667 Pulls 1 Tag Updated 1 month ago
122 Pulls 1 Tag Updated 1 month ago
No vale para practicamente nada
10 Pulls 1 Tag Updated 1 year ago
156 Pulls 1 Tag Updated 4 months ago
274 Pulls 1 Tag Updated 6 months ago
A fine-tuned Gemma 3 1B instruction model specialized for English-to-Swahili translation and Swahili conversational AI. The model accepts input in both English and Swahili but outputs responses exclusively in Swahili.
162 Pulls 7 Tags Updated 9 months ago
O melhor modelo para chatbot. Gemma3 12b quantizado, otimizado para Português Brasileiro, com chamada de tools e vision. Funciona muito bem em uma RTX3060 de 12gb.
141 Pulls 1 Tag Updated 8 months ago