Gemma 4 E2B IT Qat Mobile Transformers — Hardware Requirements & GPU Compatibility
Chat
Gemma 4 E2B IT Qat Mobile Transformers is a 2.3B-parameter open language model from Google in the Gemma 4 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 1.76 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 128K)Best on 24 GB (Q4_K_M · ~372 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~41 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 4 E2B IT Qat Mobile Transformers
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/unsloth/gemma-4-E2B-it-qat-mobile-GGUFQ4_K_M fits fully on the RTX 4090 · 21.8 GB free · 16K context
Download: gemma-4-E2B-it-qat-mobile-Q4_K_M.gguf1.40 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~133 tok/s
- generation speed
- Cost per 1M output tokens
- $0.12
- per 1M output tokens
How Much VRAM Does Gemma 4 E2B IT Qat Mobile Transformers Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | 2.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~485 tok/s | |
| 1.5 GB | 2.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~440 tok/s | |
| 1.5 GB | 2.4 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~431 tok/s | |
| 1.8 GB | 2.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~372 tok/s | |
| 2.0 GB | 2.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~324 tok/s | |
| 2.3 GB | 3.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~287 tok/s | |
| 2.7 GB | 3.5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~244 tok/s | |
| 5.0 GB | 5.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~130 tok/s |
Selected Q4_K_M
4-bit medium quantization2.2GBat 16K context
- Weights
- 1.4 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.9 GB free · ~372 tok/s
≥50 tok/s needs ≥135 GB/s · RTX 5090 ~662, RTX 3090 Ti ~372
Which Hardware Can Run Gemma 4 E2B IT Qat Mobile Transformers?
Q4_K_M · 1.8 GBGemma 4 E2B IT Qat Mobile Transformers (Q4_K_M) requires 1.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 131K context window can add up to 3.5 GB, bringing total usage to 5.2 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 IT Qat Mobile Transformers, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.8 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~281Simulate output on RTX 3080RTX 2080 Ti~228Simulate output on RTX 2080 TiRTX 3070 Ti~225Simulate output on RTX 3070 TiM3*8 GB~41Simulate output on iMac 24" M3 (8 GB)Orin Nano~38Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~27Simulate output on iPhone 1720 GB
fits · 17.9 GB free · up to 128K ctx
1 GPU
RX 7900 XT~273Simulate output on RX 7900 XT32–40 GB
fits · 29.9 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~662Simulate output on RTX 5090M5 Max36 GB~183Simulate output on Mac Studio M5 Max (36 GB)M532 GB~61Simulate output on MacBook Air 13" M5 (32 GB)Orin~76Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~50Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 4 E2B IT Qat Mobile Transformers
Gemma 4 family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| WeVisOne VL 2BTencent | — | 3.6 GB | ~328 | same size |
| LFM3 Omni 2BLiquid AI | — | 2.4 GB | ~385 | same size |
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 3.7 GB | ~323 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| SmolVLM2 2.2B InstructHugging Face | — | 2.3 GB | ~443 | same size |
Specifications
- Publisher
- Family
- Gemma 4
- Parameters
- 2.3B
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-06-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Gemma 4 E2B IT Qat Mobile Transformers need?
Gemma 4 E2B IT Qat Mobile Transformers requires 1.8 GB of VRAM at Q4_K_M, or 5.0 GB at BF16. Full 131K context adds up to 3.5 GB (5.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.3B × 4.8 bits ÷ 8 = 1.4 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 3.8 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Gemma 4 E2B IT Qat Mobile Transformers?
For Gemma 4 E2B IT Qat Mobile Transformers, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 4 E2B IT Qat Mobile Transformers on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Gemma 4 E2B IT Qat Mobile Transformers. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 4 E2B IT Qat Mobile Transformers locally?
Yes — Gemma 4 E2B IT Qat Mobile Transformers can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 4 E2B IT Qat Mobile Transformers?
At Q4_K_M, Gemma 4 E2B IT Qat Mobile Transformers can reach ~2727 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~372 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 ÷ 1.76 × 0.65 = ~2955 tok/s
Estimated speed at Q4_K_M (1.8 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 IT Qat Mobile Transformers?
At Q4_K_M, the download is about 1.40 GB. The full-precision BF16 version is 4.67 GB. The smallest option (Q2_K) is 0.99 GB.
Which GPUs can run Gemma 4 E2B IT Qat Mobile Transformers?
52 consumer GPUs can run Gemma 4 E2B IT Qat Mobile Transformers 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 IT Qat Mobile Transformers?
163 devices with unified memory can run Gemma 4 E2B IT Qat Mobile Transformers at Q4_K_M (1.8 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.