Autor: Jakub Rusinowski · Ostatnia aktualizacja: 31 marca 2026
Model library → Gemma 4 → Gemma 4 E4B
The 'Efficient 4B' (~8B total params, ~4.5B effective compute) is Gemma 4's sweet spot for 6–8 GB VRAM GPUs. Supports text + image + audio input natively. Scores higher than Gemma 3 12B on MMLU despite using far less effective compute — thanks to improved training data and the new multimodal encoder. Ideal for developers who want image OCR, voice transcription, and reasoning all in one model.
Gemma 4 E4B needs about 6 GB of VRAM at Q4 (QAT) — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 8 Billion (~4.5B effective) |
| Context window | 128,000 |
| Architecture | Dense Transformer + Multimodal Encoder (image + audio, per-layer embeddings) |
| Provider | |
| Licence | Apache 2.0 |
| Specified at | Q4 (QAT) |
| System RAM | 12 GB |
| Record updated | 2026-03-31 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 2.6 GB | 3.4 GB | ~154 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.4 GB | 4.2 GB | ~133 tok/s (est.) | Fits comfortably |
| Q4_K_M | 4.8 GB | 5.6 GB | ~107 tok/s (est.) | Fits comfortably |
| Q5_K_M | 5.7 GB | 6.5 GB | ~95 tok/s (est.) | Fits comfortably |
| Q6_K | 6.6 GB | 7.4 GB | ~86 tok/s (est.) | Fits comfortably |
| Q8_0 | 8.5 GB | 9.3 GB | ~70 tok/s (est.) | Fits comfortably |
| F16 | 16.0 GB | 16.8 GB | ~41 tok/s (est.) | Fits comfortably |
Want the memory numbers alone, at every quantization level and your own context length? Use the Gemma 4 E4B VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Gemma 4 E4B is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run gemma4:e4bWeights on Hugging Face: google/gemma-4-E4B-it.
Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| MMLU | 79.8 / 100 % | reported |
| HumanEval | 72.4 / 100 % | reported |
| MATH | 58.3 / 100 % | reported |
Best for: multimodal, image understanding, audio transcription, coding, budget hardware.
← All Gemma 4 models | VRAM calculator | Check your own hardware