Gemma 3n E2B IT — Hardware Requirements & GPU Compatibility
Vision
Gemma 3n E2B IT is a 5.4B-parameter open language model from Google in the Gemma family. At BF16 it needs about 11.97 GB of VRAM — see which GPUs and Macs can run it below.
421.3K downloads
303 likesSpecifications
- Publisher
- Family
- Gemma
- Parameters
- 5.4B
- License
- Gemma Terms
Get Started
HuggingFace
How Much VRAM Does Gemma 3n E2B IT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 12.0 GB | — | 10.88 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Gemma 3n E2B IT?
BF16 · 12.0 GBGemma 3n E2B IT (BF16) requires 12.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 16+ GB is recommended. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Gemma 3n E2B IT?
BF16 · 12.0 GB27 devices with unified memory can run Gemma 3n E2B IT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Gemma 3n E2B IT need?
Gemma 3n E2B IT requires 12.0 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 5.4B × 16 bits ÷ 8 = 10.9 GB
KV Cache + Overhead ≈ 1.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1612.0 GB- Can I run Gemma 3n E2B IT on a Mac?
Gemma 3n E2B IT requires at least 12.0 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Gemma 3n E2B IT locally?
Yes — Gemma 3n E2B IT can run locally on consumer hardware. At BF16 quantization it needs 12.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gemma 3n E2B IT?
At BF16, Gemma 3n E2B IT can reach ~244 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~55 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 12.0 × 0.55 = ~244 tok/s
Estimated speed at BF16 (12.0 GB)
~244 tok/s~55 tok/s~182 tok/s~151 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma 3n E2B IT?
At BF16, the download is about 10.88 GB.
- Which GPUs can run Gemma 3n E2B IT?
26 consumer GPUs can run Gemma 3n E2B IT at BF16 (12.0 GB). Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6700 XT. 6 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Gemma 3n E2B IT?
27 devices with unified memory can run Gemma 3n E2B IT at BF16 (12.0 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.