Gemma 4 E4B
Q4 GGUF download: google/gemma-4-E4B-it-qat-q4_0-gguf - 5.15 GB on disk, read 2026-11-19. VRAM figures above are estimates; this is the actual file size.
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
4.8
AA Index
Agentic
0.7
AA Index
Intelligence Index - Gemma 4 E4B vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-11-21.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.02 |
| Output (per 1M tokens) | $0.10 |
| Median speed (hosted API) | 70 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-11-21. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 57.6 |
| HLE | 3.8 |
| SciCode | 24.4 |
| IFBench | 44.2 |
| Terminal-Bench | 8.3 |
Source: Artificial Analysis component evals - updated 2026-11-21.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve google/gemma-4-E4B-itNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Gemma 4 E4B is a 8B-parameter apache-2.0 model from Google. It scores 4.8 on the Artificial Analysis Intelligence Index. At Q4_K_M it needs roughly 5 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
BenchmarksLink to this section
Artificial Analysis Intelligence Index - Gemma 4 E4B vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Gemma 4 E4B | 4.8 | - | 57.6 |
| Claude Fable 5.2 | 64.6 | 53.1 | - |
| GPT-6.2 Astra | 62.1 | 52.9 | - |
| Gemini 4 Neon | 61.4 | 52.1 | - |
| Gemini 4 Carbon | 60 | 50.4 | - |
| Claude Opus 5.5 | 59.1 | 51.7 | - |
Source: Artificial Analysis (2026-11-21).
PopularityLink to this section
Gemma 4 E4B has 4,354,817 downloads in the last month on HuggingFace and 1,875 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Gemma 4 E4B need?
Gemma 4 E4B with 8B parameters needs approximately 5 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Gemma 4 E4B better than other google models?
Gemma 4 E4B has 8B parameters with 131,072 context - a strong choice for multimodal, long-context, general-chat.
What license is Gemma 4 E4B under?
Gemma 4 E4B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Gemma 4 E4B well?
With 8B parameters, Gemma 4 E4B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Gemma 4 E4B?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~6 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Gemma 4 E4B's context window handle?
Gemma 4 E4B supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Gemma 4 E4B?
Gemma 4 E4B competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Can my GPU run Gemma 4 E4B?
Fit and estimated speed on popular hardware
Nearby options
Similar models and compatible hardware by spec