InternLM Models — Hardware Requirements

5 InternLM models from InternLM and the community, from the smallest that runs in 3.4 GB of VRAM up to 20B parameters. Every row links to full quantization tables and GPU compatibility.

All InternLM Models by Size

ModelParamsContext
Internlm2 5 7B Chat7B33K
Internlm 7B7B2K
Internlm3 8B Instruct8.8B33K
Internlm 20B20B4K
Internlm Chat 20B20B4K

How InternLM Compares — Benchmark Rating

Internlm 20B is the highest-rated InternLM model with an overall benchmark rating of 62.1/100 — #14 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.

GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
Composite of normalized public benchmark scores (methodology) · InternLM · other models

Frequently Asked Questions

How much VRAM do I need to run a InternLM model?
The smallest InternLM model, Internlm3 8B Instruct, runs from 3.4 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which InternLM models can I run on a 16 GB GPU?
4 of 5 InternLM models fit in 16 GB of VRAM at some quantization, including Internlm3 8B Instruct, Internlm2 5 7B Chat, Internlm 7B.
What is the most popular InternLM model to run locally?
Internlm3 8B Instruct is the most downloaded InternLM model in local-friendly quantized formats. It runs from 3.4 GB of VRAM.
How do InternLM models score on benchmarks?
Internlm 20B leads the family with an overall benchmark rating of 62.1/100, ranking #14 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.