Gemma 4 E2B — Hardware Requirements & GPU Compatibility
Chat
Gemma 4 E2B is Google DeepMind's smallest model in the Gemma 4 family, a dense architecture with roughly 5.1 billion total parameters, of which Google describes about 2.3 billion as its effective footprint at inference. This is the pretrained base checkpoint, not an instruction-tuned chat model, meant as a starting point for fine-tuning. The Gemma 4 family is multimodal — text, image, and at this size natively audio — and E2B targets efficient on-device execution on phones and laptops. It is easy to run locally, even on modest hardware once quantized. It supports a 131,072 token context window. It carries Google's Gemma 4 license terms, published as Apache 2.0 on Hugging Face with additional Gemma-specific usage terms linked from the card. Published in March 2026, it is the smallest of five sizes in the Gemma 4 lineup, aimed at mobile and edge deployment.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 128K)Best on 24 GB (Q4_K_M · ~191 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~21 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 4 E2B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/gemma-4-E2B-i1-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.5 GB free · 16K context
Download: gemma-4-E2B.i1-Q4_K_M.gguf3.43 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~68 tok/s
- generation speed
- Cost per 1M output tokens
- $0.24
- per 1M output tokens
How Much VRAM Does Gemma 4 E2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.5 GB | 2.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~259 tok/s | |
| 2.6 GB | 2.7 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~252 tok/s | |
| 2.9 GB | 3 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~230 tok/s | |
| 2.9 GB | 3.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~224 tok/s | |
| 3.4 GB | 3.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~191 tok/s | |
| 4.0 GB | 4.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~163 tok/s | |
| 4.6 GB | 4.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~143 tok/s | |
| 5.5 GB | 5.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~120 tok/s |
Selected Q4_K_M
4-bit medium quantization3.5GBat 16K context
- Weights
- 3.1 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.5 GB free · ~191 tok/s
≥50 tok/s needs ≥264 GB/s · RTX 5090 ~340, RTX 3090 Ti ~191
Which Hardware Can Run Gemma 4 E2B?
Q4_K_M · 3.4 GBGemma 4 E2B (Q4_K_M) requires 3.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 131K context window can add up to 0.7 GB, bringing total usage to 4.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Gemma 4 E2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.5 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~144Simulate output on RTX 3080RTX 2080 Ti~117Simulate output on RTX 2080 TiRTX 3070 Ti~115Simulate output on RTX 3070 TiM3*8 GB~21Simulate output on iMac 24" M3 (8 GB)Orin Nano~19Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~14Simulate output on iPhone 1720 GB
fits · 16.5 GB free · up to 128K ctx
1 GPU
RX 7900 XT~140Simulate output on RX 7900 XT32–40 GB
fits · 28.5 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~340Simulate output on RTX 5090M5 Max36 GB~94Simulate output on Mac Studio M5 Max (36 GB)M532 GB~31Simulate output on MacBook Air 13" M5 (32 GB)Orin~39Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~26Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 4 E2B
Gemma 4 family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| WeVisOne VL 4BTencent | — | 4.7 GB | ~193 | same size |
| Youtu Parsing OmniTencent | — | 12.7 GB | ~59 | same size |
| Molmo2 4BAllen AI | — | 4.7 GB | ~193 | same size |
| Xflux Text EncodersXLabs-AI | — | 12.7 GB | ~63 | same size |
| K2 Horizon 3.7BIFM | — | 11.9 GB | ~62 | same size |
| Gemma 3n E2B ITGoogle | — | 5.9 GB | ~183 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- Family
- Gemma 4
- Parameters
- 5.1B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-03-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Gemma 4 E2B need?
Gemma 4 E2B requires 3.4 GB of VRAM at Q4_K_M, or 10.6 GB at BF16. Full 131K context adds up to 0.7 GB (4.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 5.1B × 4.8 bits ÷ 8 = 3.1 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.
KV Cache + Overhead ≈ 1 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Gemma 4 E2B?
For Gemma 4 E2B, Q4_K_M (3.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (3.6 GB) provides better quality if you have the VRAM. The smallest option is IQ3_S at 2.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 4 E2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Gemma 4 E2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 4 E2B locally?
Yes — Gemma 4 E2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 4 E2B?
At Q4_K_M, Gemma 4 E2B can reach ~1399 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~191 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 ÷ 3.43 × 0.65 = ~1516 tok/s
Estimated speed at Q4_K_M (3.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 4 E2B?
At Q4_K_M, the download is about 3.07 GB. The full-precision BF16 version is 10.25 GB. The smallest option (IQ3_S) is 2.18 GB.
Which GPUs can run Gemma 4 E2B?
52 consumer GPUs can run Gemma 4 E2B 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 4 E2B?
163 devices with unified memory can run Gemma 4 E2B at Q4_K_M (3.4 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.