Google
Gemma 4 E2B
Frontier
Apr 2026Veröffentlicht128K TokenKontextApache-2.0Lizenz55 GutQualität
Gemma 4 E2B (5.099999904632568B parameters) requires approximately 5.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 7 GB of VRAM.
Loslegen
— kopieren & einfügen, um lokal auszuführenCopy-paste commands to run Gemma 4 E2B on your machine.
Run
ollama run gemma4:e2bQuick specs
Parameters5.1B
Architecturedense
Context128K tokens
Modalitytext
Min RAM2 GB
Rec. RAM3.1 GB (Q4_K_M)
LicenseApache-2.0
FamilyGemma
✓ Code✓ Chat✓ Reasoning
About this model
- •Multimodal (text+image+audio+video)
- •Per-Layer Embeddings for efficiency
- •Apache 2.0 license
- •128K context window
Verwandte Modelle
Schnellauswahl
Beste Hardware
Top-Empfehlungen für Gemma 4 E2B
Dieses Modell ausführen
Quantisierungsoptionen
VRAM-Schätzungen nach Quantisierungsstufe
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.0 GB | Low | — |
Q3_K_S | 3 | 2.5 GB | Low | — |
NVFP4 | 4 | 2.9 GB | Medium | — |
Q4_K_M | 4 | 3.1 GB | Medium | — |
Q5_K_M | 5 | 3.7 GB | High | — |
Q6_K | 6 | 4.2 GB | High | — |
Q8_0 | 8 | 5.5 GB | Very High | — |
F16 | 16 | 10.5 GB | Maximum | — |
Quality benchmarks
Gemma 4 E2B benchmark scores
Coding
SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench44.0%
Reasoning
MMLU-Pro60.0%
GPQA Diamond43.4%
MATH-500—
ARC Challenge—
Source: official · 2026-04-02
Hardware-Kompatibilität
Eignungsschätzungen für alle Hardware
Computing compatibility...
Speicheraufschlüsselung
Reference: RTX 2060 6GB
Weights3.1 GB
KV Cache0.5 GB
Runtime1.2 GB
Headroom0.6 GB
Häufig gestellte Fragen
FAQ — Gemma 4 E2B
Siehe auch