Yi 1.5 6B
by 01.AI · yi-1.5 family
6B
parameters
text-generation code-generation reasoning multilingual math
Yi 1.5 6B is the smallest model in 01.AI's Yi 1.5 series, designed for efficient local inference while maintaining strong multilingual and reasoning capabilities. It supports both English and Chinese with solid performance across general knowledge and coding tasks. At Q4 quantization, it fits easily on most consumer GPUs with 6 GB or more of VRAM, making it a practical choice for lightweight local deployments where speed and low resource usage are priorities.
Quick Start with Ollama
ollama run 6b-q4_K_M | Creator | 01.AI |
| Parameters | 6B |
| Architecture | transformer-decoder |
| Context | 4K tokens |
| Released | May 13, 2024 |
| License | Apache 2.0 |
| Ollama | yi:6b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 3.6 GB | 5 GB | | 6b-q4_K_M |
| Q8_0 | 6.4 GB | 8 GB | | 6b-q8_0 |
| F16 | 12 GB | 14 GB | | 6b-fp16 |
Compatible Hardware
Q4_K_M requires 5 GB VRAM
Benchmark Scores
63.0
mmlu