Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
9.3M Pulls 30 Tags Updated 1 week ago
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
17.1K Pulls 5 Tags Updated 1 month ago
To act as an autonomous coding assistant capable of interacting with the local file system, reading project structures, and writing executable code directly to the disk.
106 Pulls 1 Tag Updated 4 days ago
Pruned to 98 experts gemma-4 a4b 26b v5-coder. Best 20b coder model overall
73 Pulls 31 Tags Updated 6 hours ago
Gemma 4 26B-A4B (MoE, ~26B total / 4B active), vision + native tool calling
59 Pulls 2 Tags Updated 3 days ago
Gemma 4 31B dense, vision + native tool calling.
18 Pulls 1 Tag Updated 3 days ago
11 Pulls 1 Tag Updated 21 hours ago
5 Pulls 1 Tag Updated 2 hours ago
ollama run gemma4
5 Pulls 1 Tag Updated 5 days ago
3 Pulls 1 Tag Updated 20 hours ago
3 Pulls 1 Tag Updated 3 days ago
2 Pulls 1 Tag Updated 2 hours ago
2 Pulls 1 Tag Updated 2 days ago
QLoRA fine-tune of Gemma 4 E2B for scam detection. F1 86.1% / FPR 1.1% on a 300-sample real test set. 12-tool function calling for SMS, email, voice transcripts, and OCR'd MMS images.
2 Pulls 1 Tag Updated 4 days ago
Gemma4-turbo is part of the G4Turbo.com family to try and bring the Gemma 4 Model to everyone. Please visit https://g4turbo.com/ for more information about what I am doing.
17.6K Pulls 5 Tags Updated 3 days ago
1 Pull 1 Tag Updated 2 hours ago
1 Pull 1 Tag Updated an hour ago
meant for end to end disaster relief
1 Pull 1 Tag Updated yesterday
Gemma 4 Uncensored 26B (IQ4_XS) - Optimized for 16GB VRAM
3,243 Pulls 1 Tag Updated 3 weeks ago