RUN THIS LLM
Search local LLM hardware requirements
Gemma 4 E2B Base
Google · 5B · Vision
Gemma 4 base small model. ~5B params, multimodal architecture. Intended for fine-tuning and research, not direct chat use.
VRAM Requirements
| Quantization | VRAM |
|---|---|
| Q4_K_M (smallest) | 3 GB |
| Q8_0 (balanced) | 5.5 GB |
| FP16 (full quality) | 10 GB |
Specifications
- Parameters: 5B
- Category: Vision
- Max context: 128K tokens
- System RAM: 6 GB minimum
- HuggingFace: google/gemma-4-E2B
Benchmarks
- MMLU: 60 — General knowledge & reasoning (5-shot)
- HumanEval: 44 — Code generation (pass@1)
- MATH: 38 — Competition-level math reasoning
Loading interactive analysis...