Sobre

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...

Modelos Relacionados

Google: Gemma 4 26B A4B 2026-04-03 Gemma 4 E4B (Reasoning)2026-04-03 Gemma 4 E4B (Non-reasoning)2026-04-03 Google: Gemma 4 26B A4B (free)2026-04-03 Gemma 4 31B (Reasoning)2026-04-02 Gemma 4 31B (Non-reasoning)2026-04-02 Gemma 4 26B A4B (Reasoning)2026-04-02 Gemma 4 26B A4B (Non-reasoning)2026-04-02

Open Source

HuggingFace

apache-2.031BGGUF / GPTQ / AWQ

Downloads

498.3K

Curtidas

386

VRAM (FP16)

24-48 GB

GPU

A6000 / M3 Ultra

Google: Gemma 4 31B

Sobre

Modelos Relacionados

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Open Source

Comparação Rápida

Modelos Similares