What are the hardware requirements for Internlm2 20B?

Internlm2 20B requires approximately 39.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Internlm2 20B and how large is it?

Internlm2 20B is developed by internlm, a model with 20b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Internlm2 20B perform on standard benchmarks?

Internlm2 20B has the following published scores: MMLU 67.58. Compare against reference models on this page or on the LLM Explorer leaderboards.

Internlm2 20B by internlm — VRAM 39.7GB, 32K context

Name: Internlm2 20B
Author: internlm

Internlm2 20B is an open-source language model by internlm. Features: 20b LLM, VRAM: 39.7GB, Context: 32K, License: other, LLM Explorer Score: 0.16, Arc: 63, HellaSwag: 83.2, MMLU: 67.6, GSM8K: 67.9.

Arxiv:2403.17297 Custom code Internlm2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/internlm/internlm2-20b

Internlm2 20B Parameters and Internals

Model Type

text generation, AI assistant

Use Cases

Areas:

research, commercial applications

Applications:

general text generation, chat applications, long-text processing

Primary Use Cases:

instruction adherence, empathetic chatting, tool invocation

Limitations:

Potential biases, may produce harmful content

Considerations:

Ethical considerations must guide deployment, especially for chat or interactive applications.

Supported Languages

English (high), Chinese (high)

Training Details

Data Sources:

domain-specific corpus

Methodology:

RLHF (Reinforcement Learning from Human Feedback)

Context Length:

200000

Model Architecture:

Transformer-based

Safety Evaluation

Ethical Considerations:

Model may produce unexpected outputs including biases or discrimination.

Responsible Ai Considerations

Transparency:

Results based on probabilistic model outputs.

Accountability:

Users are responsible for usage consequences.

Mitigation Strategies:

Safety features encouraged, but not guaranteed to prevent all adverse outputs.

Input Output

Input Format:

Text input; maximum context length of 200,000 characters.

Accepted Modalities:

text

Output Format:

Text output

Performance Tips:

Using float16 precision on a capable GPU recommended to avoid out-of-memory issues.

LLM Name	Internlm2 20B
Repository 🤗	https://huggingface.co/internlm/internlm2-20b
Model Size	20b
Required VRAM	39.7 GB
Updated	2026-08-04
Maintainer	internlm
Model Type	internlm2
Model Files	9.9 GB: 1-of-4 10.0 GB: 2-of-4 9.9 GB: 3-of-4 9.9 GB: 4-of-4
Model Architecture	InternLM2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.0
Is Biased	0
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Vocabulary Size	92544
Torch Data Type	bfloat16

Rank the Internlm2 20B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Internlm2 20B

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 20B	256K / 39.7 GB	158	17
Internlm2 5 20B Chat	32K / 39.7 GB	7642	96
Internlm2 Chat 20B ExPO	32K / 39.8 GB	15821	1
Internlm2 Chat 20B	32K / 39.7 GB	20635	88
Internlm2 Base 20B	32K / 39.7 GB	15804	8
...ternlm2 5 20B Chat Abliterated	32K / 39.7 GB	16	4
ChemLLM 20B Chat DPO	32K / 40.6 GB	33	10
ChemLLM 20B Chat SFT	32K / 40.6 GB	44	5
Internlm Chatbode 20B	32K / 39.8 GB	4	1
MathGenie InterLM 20B	32K / 39.8 GB	12	10

Note: green Score (e.g. "73.2") means that the model is better than internlm/internlm2-20b.