Autor: Jakub Rusinowski · Ostatnia aktualizacja: 10 lipca 2026
High-performance models from 01.AI. Known for strong bilingual (English/Chinese) capabilities and coding performance.
| Yi 1.5 34B Chat | Min 20 GB VRAM · Q4_K_M · 32,000 ctx · ollama run yi:34b |
| Yi 1.5 9B Chat | Min 8 GB VRAM · Q4_K_M · 32,000 ctx · ollama run yi:9b |
The cheapest GPU that runs Yi 1.5 Family locally (min 8 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run yi:34b
Minimum VRAM: 8 GB. For best results use Q4_K_M quantization.
Yi 1.5 Family needs about 8 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Yi 1.5 34B Chat (20 GB, Q4_K_M); Yi 1.5 9B Chat (8 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Yi 1.5 Family runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Yi 1.5 Family in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run yi:34b. This downloads Yi 1.5 Family and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.