RUN THIS LLM
Search local LLM hardware requirements
Gemma 2 27B
Google · 27B · General
Previous-gen large Gemma. Reliable for production workloads requiring good general performance.
VRAM Requirements
| Quantization | VRAM |
|---|---|
| Q4_K_M (smallest) | 16.2 GB |
| Q8_0 (balanced) | 29.7 GB |
| FP16 (full quality) | 54 GB |
Specifications
- Parameters: 27B
- Category: General
- Max context: 8K tokens
- System RAM: 24 GB minimum
- HuggingFace: google/gemma-2-27b-it
Benchmarks
- MMLU: 78 — General knowledge & reasoning (5-shot)
- HumanEval: 65 — Code generation (pass@1)
- MATH: 46 — Competition-level math reasoning
Loading interactive analysis...