Google

company

Verified

AI & ML interests

Google ❤️ Open Source AI

Recent Activity

pannaga10 new activity about 7 hours ago

google/gemma-4-31B-it:Gemma4 is super slow on vllm docker , max to max 15 token per second only (4 X L4 GPU)

hadamelino submitted a paper about 8 hours ago

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

MaartenGr updated a model about 11 hours ago

google/gemma-4-E2B-it-assistant

View all activity

Papers

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency

View all Papers

in google/gemma-4-31B-it about 7 hours ago

Gemma4 is super slow on vllm docker , max to max 15 token per second only (4 X L4 GPU)

#102 opened 2 days ago by

submitted a paper to Daily Papers about 8 hours ago

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

Paper • 2605.00933 • Published 11 days ago • 2

updated 4 models about 11 hours ago

google/gemma-4-E2B-it-assistant

Any-to-Any • 78M • Updated about 11 hours ago • 7.01k • 44

google/gemma-4-31B-it-assistant

Any-to-Any • 0.5B • Updated about 11 hours ago • 66.6k • 206

google/gemma-4-E4B-it-assistant

Any-to-Any • 78.8M • Updated about 11 hours ago • 51.8k • 63

google/gemma-4-26B-A4B-it-assistant

Any-to-Any • 0.4B • Updated about 11 hours ago • 47.7k • 111

submitted a paper to Daily Papers about 17 hours ago

A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency

Paper • 2605.06924 • Published 5 days ago • 12

lucianommartins

in google/gemma-4-26B-A4B-it 2 days ago

fix(chat_template): Emit multimodal placeholders in tool response content-parts

#38 opened 10 days ago by

in google/gemma-4-26B-A4B-it 3 days ago

GGUF available — Cerebellum v3 (11 GB, ablation-guided mixed-precision)

#37 opened 11 days ago by

in google/gemma-4-E2B 4 days ago

Can't run Gemma4 locally

#6 opened 6 days ago by

in google/gemma-4-31B-it 4 days ago

This model is so good, but the KV cache ruins it.

#100 opened 6 days ago by

UniversalLove333

in google/gemma-4-E2B-it 4 days ago

Fix lineage

#31 opened 5 days ago by

in google/gemma-4-E4B-it 4 days ago

Fix lineage

#31 opened 5 days ago by

in google/gemma-4-26B-A4B-it 4 days ago

Fix lineage

#41 opened 5 days ago by

in google/gemma-4-31B-it 4 days ago

Add proper metadata

#101 opened 5 days ago by

submitted a paper to Daily Papers 5 days ago

How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum

Paper • 2604.25907 • Published 14 days ago • 3

in google/gemma-4-E2B-it 5 days ago

Fix lineage

#31 opened 5 days ago by

in google/gemma-4-E4B-it 5 days ago

Fix lineage

#31 opened 5 days ago by

in google/gemma-4-26B-A4B-it 5 days ago

Fix lineage

#41 opened 5 days ago by

in google/gemma-4-31B-it 5 days ago

Add proper metadata

#101 opened 5 days ago by