Gemma 3n E2B IT — Hardware Requirements & GPU Compatibility
Vision
Gemma 3n E2B is the smaller of Google's two Gemma 3n instruction-tuned models, designed for phones, laptops and other on-device use. "E2B" stands for an effective size of about 2 billion parameters: the raw checkpoint holds around 5.4 billion, but techniques such as per-layer embeddings let it run with a memory footprint closer to a 2B model. It accepts text, image and audio input and generates text. The model has a 32K-token context window and is released under Google's Gemma terms of use. At 4-bit quantization it needs only a few gigabytes of memory, so it runs on almost any modern GPU, laptop or recent phone.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~183 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~20 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 3n E2B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run gemma3n:e2bQ4_K_M fits fully on the RTX 4090 · 18.1 GB free · 16K context
Download: gemma-3n-E2B-it-Q4_K_M.gguf3.03 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · Q4_K_M
- Generation speed
- ~65 tok/s
- generation speed
- Cost per 1M output tokens
- $0.35
- per 1M output tokens
How Much VRAM Does Gemma 3n E2B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.5 GB | 7.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~258 tok/s | |
| 2.6 GB | 7.6 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~250 tok/s | |
| 2.9 GB | 7.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~224 tok/s | |
| 3.0 GB | 7.9 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~219 tok/s | |
| 3.6 GB | 8.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~183 tok/s | |
| 4.3 GB | 9.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~154 tok/s | |
| 4.9 GB | 9.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~133 tok/s | |
| 6.0 GB | 10.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~110 tok/s |
Selected Q4_K_M
4-bit medium quantization5.9GBat 16K context
- Weights
- 3.0 GB
- KV cache
- 2.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.1 GB free · ~183 tok/s
≥50 tok/s needs ≥276 GB/s · RTX 5090 ~325, RTX 3090 Ti ~183
Which Hardware Can Run Gemma 3n E2B IT?
Q4_K_M · 3.6 GBGemma 3n E2B IT (Q4_K_M) requires 3.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Gemma 3n E2B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.1 GB free · up to 16K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~138Simulate output on RTX 3080RTX 2080 Ti~112Simulate output on RTX 2080 TiRTX 3070 Ti~110Simulate output on RTX 3070 TiM3*8 GB~20Simulate output on iMac 24" M3 (8 GB)Orin Nano~19Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~13Simulate output on iPhone 1720 GB
fits · 14.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~134Simulate output on RX 7900 XT32–40 GB
fits · 26.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~325Simulate output on RTX 5090M5 Max36 GB~90Simulate output on Mac Studio M5 Max (36 GB)M532 GB~30Simulate output on MacBook Air 13" M5 (32 GB)Orin~37Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~24Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 3n E2B IT
Gemma 3 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Youtu Parsing OmniTencent | — | 12.7 GB | ~59 | same size |
| Qwen2.5 Omni 3BAlibaba | — | 6 GB | ~180 | same size |
| TLive Omni 4BTaoLiveAIGC | — | 13.3 GB | ~54 | same size |
| K2 Horizon 3.7BIFM | — | 11.9 GB | ~62 | same size |
| Gemma 4 E2BGoogle | — | 3.5 GB | ~191 | same size |
| T5gemma 2B 2B Ul2Google | — | 6 GB | ~178 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- Family
- Gemma 3
- Parameters
- 5.4B
- Release Date
- 2025-06-12
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3n E2B IT need?
Gemma 3n E2B IT requires 3.6 GB of VRAM at Q4_K_M, or 12.0 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 5.4B × 4.8 bits ÷ 8 = 3.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Gemma 3n E2B IT?
For Gemma 3n E2B IT, Q4_K_M (3.6 GB) offers the best balance of quality and VRAM usage. Q4_K_L (3.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.6 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3n E2B IT on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Gemma 3n E2B IT. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 3n E2B IT locally?
Yes — Gemma 3n E2B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3n E2B IT?
At Q4_K_M, Gemma 3n E2B IT can reach ~1337 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~183 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 3.5900 × 0.65 = ~1448 tok/s
Estimated speed at Q4_K_M (3.6 GB)
Real-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 Q4_K_M, the download is about 3.26 GB. The full-precision BF16 version is 10.88 GB. The smallest option (IQ2_XXS) is 1.50 GB.
Which GPUs can run Gemma 3n E2B IT?
52 consumer GPUs can run Gemma 3n E2B IT at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Gemma 3n E2B IT?
163 devices with unified memory can run Gemma 3n E2B IT at Q4_K_M (3.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.