Gemma 3n E4B IT — Hardware Requirements & GPU Compatibility
Vision
Gemma 3n E4B IT is the instruction-tuned variant of Google's Gemma 3n E4B, a multimodal model built for on-device use on phones, laptops, and tablets that accepts text, image, audio, and video input and can perform automatic speech recognition and speech translation alongside text chat. It uses Google's MatFormer (Matryoshka Transformer) architecture, which nests a smaller sub-model inside the full network so the same checkpoint can run at reduced effective capacity, and Per-Layer Embedding, which caches embedding parameters to fast local storage instead of holding them all in memory. The "E4B" designation refers to an effective parameter count of around 4 billion at inference, even though the checkpoint's total parameters are larger; either way it is light enough for a single consumer GPU or even a high-end phone. Context length is 32,768 tokens. It is released under Google's Gemma Terms of Use, a custom license permitting broad commercial and research use alongside a prohibited-use policy, and was published in June 2025.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~127 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~27 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 3n E4B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run gemma3n:e4bQ4_K_M fits fully on the RTX 4090 · 16.3 GB free · 16K context
Download: gemma-3n-E4B-it-Q4_K_M.gguf4.54 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (4 GB headroom) · Q4_K_M
- Generation speed
- ~45 tok/s
- generation speed
- Cost per 1M output tokens
- $0.51
- per 1M output tokens
How Much VRAM Does Gemma 3n E4B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.7 GB | 9.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~179 tok/s | |
| 3.8 GB | 9.3 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~173 tok/s | |
| 4.2 GB | 9.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~156 tok/s | |
| 4.3 GB | 9.8 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~152 tok/s | |
| 5.2 GB | 10.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~127 tok/s | |
| 6.2 GB | 11.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~107 tok/s | |
| 7.1 GB | 12.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~92 tok/s | |
| 8.6 GB | 14.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~76 tok/s |
Selected Q4_K_M
4-bit medium quantization7.7GBat 16K context
- Weights
- 4.5 GB
- KV cache
- 2.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.3 GB free · ~127 tok/s
≥50 tok/s needs ≥398 GB/s · RTX 5090 ~225, RTX 3090 Ti ~127
Which Hardware Can Run Gemma 3n E4B IT?
Q4_K_M · 5.2 GBGemma 3n E4B IT (Q4_K_M) requires 5.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Gemma 3n E4B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 0.3 GB free · up to 16K ctx
16 GPUs · 1 device family
RTX 3080~95Simulate output on RTX 3080RTX 2080 Ti~77Simulate output on RTX 2080 TiRTX 3070 Ti~76Simulate output on RTX 3070 TiOrin Nano~13Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.3 GB free · up to 32K ctx
1 GPU
RX 7900 XT~93Simulate output on RX 7900 XT32–40 GB
fits · 24.3 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~225Simulate output on RTX 5090M5 Max36 GB~62Simulate output on Mac Studio M5 Max (36 GB)M532 GB~21Simulate output on MacBook Air 13" M5 (32 GB)Orin~26Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~17Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Gemma 3n E4B IT?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1317.5
#96/187 open
Alternatives to Gemma 3n E4B IT
Gemma 3 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
Fine-tunes & variants(3)
Specifications
- Publisher
- Family
- Gemma 3
- Parameters
- 7.8B
- Release Date
- 2025-06-03
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3n E4B IT need?
Gemma 3n E4B IT requires 5.2 GB of VRAM at Q4_K_M, or 17.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 7.8B × 4.8 bits ÷ 8 = 4.7 GB
KV Cache + Overhead ≈ 0.5 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 E4B IT?
For Gemma 3n E4B IT, Q4_K_M (5.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3n E4B IT on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Gemma 3n E4B IT. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 3n E4B IT locally?
Yes — Gemma 3n E4B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3n E4B IT?
At Q4_K_M, Gemma 3n E4B IT can reach ~927 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~127 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 ÷ 5.18 × 0.65 = ~1004 tok/s
Estimated speed at Q4_K_M (5.2 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 E4B IT?
At Q4_K_M, the download is about 4.71 GB. The full-precision BF16 version is 15.70 GB. The smallest option (IQ2_XXS) is 2.16 GB.
Which GPUs can run Gemma 3n E4B IT?
52 consumer GPUs can run Gemma 3n E4B 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 E4B IT?
151 devices with unified memory can run Gemma 3n E4B IT at Q4_K_M (5.2 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.