Yi 1.5 9B
by 01.AI · yi-1.5 family
9B
parameters
text-generation code-generation reasoning multilingual math
Yi 1.5 9B is the mid-range model in 01.AI's Yi 1.5 family, offering a strong balance of capability and efficiency. It delivers improved reasoning and multilingual performance over the 6B variant while remaining accessible on consumer hardware. With Q4 quantization requiring only around 6.5 GB of VRAM, it runs well on 8 GB GPUs and Apple Silicon Macs. A solid choice for users who want better quality than the 6B without jumping to the much larger 34B model.
Quick Start with Ollama
ollama run 9b-q4_K_M | Creator | 01.AI |
| Parameters | 9B |
| Architecture | transformer-decoder |
| Context | 4K tokens |
| Released | May 13, 2024 |
| License | Apache 2.0 |
| Ollama | yi:9b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 5.5 GB | 6.5 GB | | 9b-q4_K_M |
| Q8_0 | 9.5 GB | 11 GB | | 9b-q8_0 |
| F16 | 18 GB | 20 GB | | 9b-fp16 |
Compatible Hardware
Q4_K_M requires 6.5 GB VRAM
Benchmark Scores
69.0
mmlu