Will It Run AI

GoogleGoogle

Gemma 4 E4B

Frontera
Apr 2026Publicado128K tokensContextoApache-2.0Licencia65 BuenoCalidad

Gemma 4 E4B (8B parameters) requires approximately 8.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.

Comenzar

— copia y pega para ejecutar en local

Copy-paste commands to run Gemma 4 E4B on your machine.

Run

ollama run gemma4:e4b

Quick specs

Parameters8B
Architecturedense
Context128K tokens
Modalitytext
Min RAM3.1 GB
Rec. RAM4.9 GB (Q4_K_M)
LicenseApache-2.0
FamilyGemma
Code Chat Reasoning

About this model

Gemma 4 E4B is Google's mid-range on-device model with 8B total parameters (4.5B effective). Default Gemma 4 model on Ollama. Supports text and image. Apache 2.0 licensed.

  • Multimodal (text+image+audio+video)
  • Default Gemma 4 on Ollama
  • Apache 2.0 license
  • 128K context

Modelos relacionados

Tu hardware

Detectando...

Selecciones rápidas

Mejor hardware

Mejores opciones para Gemma 4 E4B

Ejecutar este modelo

Opciones de cuantización

Estimaciones de VRAM por nivel de cuantización

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
Low
Q3_K_S
3
3.9 GB
Low
NVFP4
4
4.5 GB
Medium
Q4_K_M
4
4.9 GB
Medium
Q5_K_M
5
5.8 GB
High
Q6_K
6
6.6 GB
High
Q8_0
8
8.6 GB
Very High
F16
16
16.4 GB
Maximum

Quality benchmarks

Gemma 4 E4B benchmark scores

Benchmark verified

Coding

SWE-bench Verified
HumanEval+
Aider Polyglot
LiveCodeBench52.0%

Reasoning

MMLU-Pro69.4%
GPQA Diamond58.6%
MATH-500
ARC Challenge

Source: official · 2026-04-02

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

Weights4.9 GB
KV Cache1.3 GB
Runtime1.2 GB
Headroom0.6 GB

Preguntas frecuentes

FAQ — Gemma 4 E4B

Ver también