BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Gemma 4 31B

By Google · United States

Updated 2026-07-13

chat general vision audio multilingual
Parameters
31B
License
Gemma
Context
250k
VRAM (Q4)
18 GB
Released
April 2026

Overview

Google's dense 31B multimodal model with native text, image, and audio support across 140+ languages. Ranked #3 on Chatbot Arena's open leaderboard with a 256K context window.

When to pick this model

  • Multilingual production apps spanning 100+ languages
  • Native audio input and analysis workflows
  • Long-context document and codebase analysis
  • On-prem multimodal chat backends
  • Replacing GPT-4o-class APIs with local weights

VRAM requirements by quantization

VRAM REQUIRED (GB)81216243248Q4_K_M18 GBQ5_K_M22 GBQ8_033 GBFP1662 GB
QuantizationVRAM required
Q4_K_M (recommended)18 GB
Q5_K_M22 GB
Q8_033 GB
FP16 (no quantization)62 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, Gemma 4 31B wants a 24 GB card at Q4_K_M (18 GB). Stepping up to Q8_0 nearly doubles the footprint to 33 GB, and unquantized FP16 weights take 62 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, Gemma 4 31B needs roughly 32 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 3 tokens/sec on entry-level GPUs, on the order of 12 tokens/sec on a mid-range card, and up to 30 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches Gemma 4 31B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for Gemma 4 31B
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBDoes not fit — needs 18 GB at Q4_K_M
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopDoes not fit — needs 18 GB at Q4_K_M
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTDoes not fit — needs 18 GB at Q4_K_M
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopQ5_K_M (22 GB used)
32 GBRTX 5090Q5_K_M (22 GB used)

Which GPU should you buy to run Gemma 4 31B?

To run Gemma 4 31B locally at Q4, you need ~18 GB of VRAM. The best value for this is a RTX 4090 (24 GB VRAM).

Check RTX 4090 price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Strengths

  • #3 on Chatbot Arena's open leaderboard
  • Native audio understanding, not just text-to-image
  • 256K context window in a dense 31B model
  • Strong coverage across 140+ languages
  • Backed by Google's training infrastructure

Limitations

  • Gemma license is more restrictive than Apache 2.0
  • 31B dense model needs ~20GB VRAM in Q4
  • Audio quality trails purpose-built ASR models

Typical workloads

In our catalog grid, Gemma 4 31B is filed under Advanced Multimodal, Audio + Vision, Writing — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: vision-language work — screenshots, charts, scanned documents; audio understanding; multilingual workloads.

The 250k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. It ships under the Gemma license — commercial use is generally possible but read the specific terms before embedding it in a product.

Architecture & training

Architecture: Dense 31B · multimodal text+image+audio · 256k ctx

Training: 140+ languages.

Verdict

The best open multimodal generalist of the Gemma line, assuming you can live with the Gemma license.

Quick start

ollama run gemma4:31b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does Gemma 4 31B need?

At the recommended Q4_K_M quantization, Gemma 4 31B needs about 18 GB of VRAM. Q8_0 takes 33 GB, and unquantized FP16 weights take 62 GB.

Can Gemma 4 31B run without a GPU?

Yes — with roughly 32 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does Gemma 4 31B support?

Gemma 4 31B supports a 250k-token context window (256,000 tokens).

Can I use Gemma 4 31B commercially?

Gemma 4 31B ships under the Gemma license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.

How fast is Gemma 4 31B on consumer hardware?

Our compatibility engine estimates on the order of 12 tokens/sec on a mid-range GPU and up to 30 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of Gemma 4 31B should I download first?

Start with Q4_K_M (18 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.

Tools

Is Gemma 4 31B the right pick for you?

Compute self-hosted ROI → Back to catalog