Gemma 4 E4B IT — Hardware Requirements & GPU Compatibility
ChatFunctions
Gemma 4 E4B IT packs Google's Gemma 4 architecture into a compact, roughly 8-billion-parameter footprint, positioned as the mid-sized option in Gemma 4's efficiency-focused E-series alongside the smaller E2B variant. It is tuned for chat and instruction-following rather than multimodal input, focusing on dialogue quality within a lightweight package. Parameter counts in this range are well suited to local inference on a single consumer GPU, even at higher precision, and comfortably so once quantized. The model provides a 128K token context window, sufficient for most chat and document-assistance use cases without needing the largest Gemma 4 variants. It is released under the Apache 2.0 license, and was published on March 2, 2026, shortly before the larger dense and mixture-of-experts Gemma 4 models that followed.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 64K)Best on 24 GB (Q4_K_M · ~123 tok/s · 128K)Macs from 8 GB (IQ3_M · ~17 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 4 E4B IT
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-E4B-it-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 18.4 GB free · 16K context
Download: gemma-4-E4B-it-Q4_K_M.gguf4.98 GBunsloth
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 3080 Ti (12 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~112 tok/s
- generation speed
- Cost per 1M output tokens
- $0.30
- per 1M output tokens
How Much VRAM Does Gemma 4 E4B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.9 GB | 4.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~167 tok/s | |
| 4.0 GB | 4.6 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~163 tok/s | |
| 4.4 GB | 5 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~148 tok/s | |
| 4.5 GB | 5.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~145 tok/s | |
| 5.3 GB | 5.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~123 tok/s | |
| 6.2 GB | 6.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~105 tok/s | |
| 7.1 GB | 7.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~92 tok/s | |
| 8.5 GB | 9.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~77 tok/s |
Selected Q4_K_M
4-bit medium quantization5.6GBat 16K context
- Weights
- 4.8 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.4 GB free · ~123 tok/s
≥50 tok/s needs ≥409 GB/s · RTX 5090 ~219, RTX 3090 Ti ~123
Which Hardware Can Run Gemma 4 E4B IT?
Q4_K_M · 5.3 GBGemma 4 E4B IT (Q4_K_M) requires 5.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 131K context window can add up to 2.9 GB, bringing total usage to 8.2 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Gemma 4 E4B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.4 GB free · up to 64K ctx
16 GPUs · 1 device family
RTX 3080~93Simulate output on RTX 3080RTX 2080 Ti~75Simulate output on RTX 2080 TiRTX 3070 Ti~74Simulate output on RTX 3070 TiOrin Nano~13Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 14.4 GB free · up to 128K ctx
1 GPU
RX 7900 XT~90Simulate output on RX 7900 XT32–40 GB
fits · 26.4 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~219Simulate output on RTX 5090M5 Max36 GB~61Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~25Simulate 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
Alternatives to Gemma 4 E4B IT
Gemma 4 family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | 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 |
| InternVL3 5 8BOpenGVLab | — | 8.2 GB | ~116 | same size |
Fine-tunes & variants(15)
- ContextPilot E4B
- Gemma 4 E4B IT
- Gemma 4 E4B IT OBLITERATED
- Gemma 4 E4B IT Qat Mobile Transformers
- Gemma 4 E4B IT Qat Q4 0 Unquantized
- Gemma 4 E4B IT Ultra Uncensored Heretic
- Gemma 4 E4B IT Uncensored
- Gemma 4 E4B Luchador
- Gemma 4 E4B Luchador Rudo
- Gemma4 E4b Toolcall V01 Lora
- Kizagan E4B Turkish Reasoning Model
- NVIDIA Nemotron 3.5 Bolt E4B BF16
- OTel LLM E4B IT
- Supergemma4 E4b Abliterated
- Supergemma4 E4b Abliterated Litert Lm
Specifications
- Publisher
- Family
- Gemma 4
- Parameters
- 8.0B
- 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 E4B IT need?
Gemma 4 E4B IT requires 5.3 GB of VRAM at Q4_K_M, or 16.5 GB at BF16. Full 131K context adds up to 2.9 GB (8.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.0B × 4.8 bits ÷ 8 = 4.8 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.
KV Cache + Overhead ≈ 3.4 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Gemma 4 E4B IT?
For Gemma 4 E4B IT, Q4_K_M (5.3 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 3.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 4 E4B IT on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Gemma 4 E4B IT, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run Gemma 4 E4B IT locally?
Yes — Gemma 4 E4B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 4 E4B IT?
At Q4_K_M, Gemma 4 E4B IT can reach ~902 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~123 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 ÷ 5.32 × 0.65 = ~977 tok/s
Estimated speed at Q4_K_M (5.3 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 E4B IT?
At Q4_K_M, the download is about 4.80 GB. The full-precision BF16 version is 15.99 GB. The smallest option (IQ2_M) is 2.70 GB.
Which GPUs can run Gemma 4 E4B IT?
52 consumer GPUs can run Gemma 4 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 4 E4B IT?
151 devices with unified memory can run Gemma 4 E4B IT at Q4_K_M (5.3 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.