作者： Jakub Rusinowski · 最后更新： 2026年7月10日
LG AI Research's flagship open-source model family with top-tier real-world usability scores across 20 benchmarks. Excels at instruction-following and long-context tasks in both English and Korean. MIT licensed for commercial use.
| EXAONE 3.5 2.4B | Min 2 GB VRAM · Q4_K_M · 32,768 ctx · ollama run exaone3.5:2.4b |
| EXAONE 3.5 7.8B | Min 6 GB VRAM · Q4_K_M · 32,768 ctx · ollama run exaone3.5:7.8b |
| EXAONE 3.5 32B | Min 20 GB VRAM · Q4_K_M · 32,768 ctx · ollama run exaone3.5:32b |
The cheapest GPU that runs EXAONE 3.5 locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run exaone3.5:2.4b
Minimum VRAM: 2 GB. For best results use Q4_K_M quantization.
EXAONE 3.5 needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: EXAONE 3.5 2.4B (2 GB, Q4_K_M); EXAONE 3.5 7.8B (6 GB, Q4_K_M); EXAONE 3.5 32B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — EXAONE 3.5 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 EXAONE 3.5 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 exaone3.5:2.4b. This downloads EXAONE 3.5 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.