AI Agent Hub

LLM Models · google

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

59 models from google Compare
gemma-4-31B-it-qat-w4a16-ct logo
gemma-4-31B-it-qat-w4a16-ct
google

Hugging Face GitHub Launch Blog Documentation Technical Report License : Apache 2.0 Authors : Google DeepMind

open-source 31.0B ★ 30.0 ↓ 1.2M
gemma-4-31B logo
gemma-4-31B
google

Hugging Face GitHub Launch Blog Documentation Technical Report License : Apache 2.0 Authors : Google DeepMind

open-source 31.0B ★ 30.0 ↓ 717.3K
Google: Gemma 4 31B (free) logo
Google: Gemma 4 31B (free)
google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

closed-source ★ 30.0
Google: Gemma 4 31B (batch) logo
Google: Gemma 4 31B (batch)
google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

closed-source ★ 30.0
gemma-4-26B-A4B-it logo
gemma-4-26B-A4B-it
google

Hugging Face GitHub Launch Blog Documentation Technical Report License : Apache 2.0 Authors : Google DeepMind

open-source 26.0B ★ 26.0 ↓ 8.2M
gemma-4-26B-A4B-it-qat-q4_0-unquantized logo
gemma-4-26B-A4B-it-qat-q4_0-unquantized
google

Hugging Face GitHub Launch Blog Documentation Technical Report License : Apache 2.0 Authors : Google DeepMind

open-source 26.0B ★ 26.0 ↓ 239.8K
Google: Gemma 4 26B A4B  (free) logo
Google: Gemma 4 26B A4B (free)
google

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

closed-source ★ 26.0
diffusiongemma-26B-A4B-it logo
diffusiongemma-26B-A4B-it
google

Hugging Face GitHub Launch Blog Documentation License : Apache 2.0 Authors : Google DeepMind

open-source 26.0B ★ 13.0 ↓ 1.3M
Google: Gemini 3 Flash Preview (batch) logo
Google: Gemini 3 Flash Preview (batch)
google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

multimodal ★ 4.0
Google: Gemini 3 Flash Preview logo
Google: Gemini 3 Flash Preview
google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

multimodal ★ 4.0
gemma-3-270m logo
gemma-3-270m
google

open-source 0.27B ★ 2.0 ↓ 1.4M
gemma-3-1b-it logo
gemma-3-1b-it
google

open-source 1.0B ↓ 3.2M