Gemma 3 4B
By Google · United States
Updated 2026-07-13
Overview
Google's compact multimodal 4B with 128K context, vision input, and 140+ language coverage. The smallest Gemma 3 with the full feature set intact.
When to pick this model
- You need vision and long context on a low-VRAM machine or edge device
- You're shipping multilingual apps and need broad language coverage
- You want one small model for both text and image inputs
- You're prototyping before scaling to 12B or 27B
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 10 GB |
| Q5_K_M | 12 GB |
| Q8_0 | 18 GB |
| FP16 (no quantization) | 33 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 3 4B needs a 12 GB card at Q4_K_M (10 GB). Stepping up to Q8_0 nearly doubles the footprint to 18 GB, and unquantized FP16 weights take 33 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Gemma 3 4B needs roughly 12 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 14 tokens/sec on entry-level GPUs, on the order of 40 tokens/sec on a mid-range card, and up to 100 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Gemma 3 4B 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 memory | Example cards | Best fit for Gemma 3 4B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 10 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Q5_K_M (12 GB used) |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Q5_K_M (12 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q8_0 (18 GB used) |
| 32 GB | RTX 5090 | Q8_0 (18 GB used) |
Which GPU should you buy to run Gemma 3 4B?
To run Gemma 3 4B locally at Q4, you need ~10 GB of VRAM. The best value for this is a RTX 5070 (12 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Multimodal in a 4B footprint
- 140+ language coverage
- 128K context
- Sliding-window attention keeps memory in check
Limitations
- Gemma License — review terms before commercial use
- Trails the 12B and 27B on reasoning and code
Typical workloads
In our catalog grid, Gemma 3 4B is filed under Compact Multilingual, Laptop Vision, Edge — 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; multilingual workloads.
The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. 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 · multimodal text+vision · sliding-window attention (5:1 local:global)
Training: 4T tokens, 140+ languages.
The most capable 4B multimodal you can run locally — strong default for resource-constrained deployments.
Quick start
ollama run gemma3:4bOr 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 3 4B need?
At the recommended Q4_K_M quantization, Gemma 3 4B needs about 10 GB of VRAM. Q8_0 takes 18 GB, and unquantized FP16 weights take 33 GB.
Can Gemma 3 4B run without a GPU?
Yes — with roughly 12 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 3 4B support?
Gemma 3 4B supports a 125k-token context window (128,000 tokens).
Can I use Gemma 3 4B commercially?
Gemma 3 4B 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 3 4B on consumer hardware?
Our compatibility engine estimates on the order of 40 tokens/sec on a mid-range GPU and up to 100 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Gemma 3 4B should I download first?
Start with Q4_K_M (10 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 Q8_0.