作者： Jakub Rusinowski · 最后更新： 2025年1月15日
来自中国上海AI实验室的强大开源模型。InternLM 3在中英双语任务、编程和长文档分析方面表现出色。在数学和STEM推理方面尤为突出，是中文语言应用的顶级开源选择。
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | InternLM 3 8B Instruct, InternLM 3 20B Instruct |
| InternLM 3 8B Instruct | Min 6 GB VRAM · Q4_K_M · 32,768 ctx · ollama run internlm3:8b |
| InternLM 3 20B Instruct | Min 13 GB VRAM · Q4_K_M · 32,768 ctx · ollama run internlm3:20b |
The cheapest GPU that runs InternLM 3 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run internlm3:8b
Minimum VRAM: 6 GB. For best results use Q4_K_M quantization.
InternLM 3 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: InternLM 3 8B Instruct (6 GB, Q4_K_M); InternLM 3 20B Instruct (13 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — InternLM 3 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 InternLM 3 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 internlm3:8b. This downloads InternLM 3 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.