What are the hardware requirements for Internlm2 7B?

Internlm2 7B requires approximately 15.5 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 7B and how large is it?

Internlm2 7B is developed by internlm, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Internlm2 7B perform on standard benchmarks?

Internlm2 7B has the following published scores: MMLU 65.24. Compare against reference models on this page or on the LLM Explorer leaderboards.

Internlm2 7B by internlm — VRAM 15.5GB, 32K context

Name: Internlm2 7B
Author: internlm

Internlm2 7B is an open-source language model by internlm. Features: 7b LLM, VRAM: 15.5GB, Context: 32K, License: other, HF Score: 66.7, LLM Explorer Score: 0.23, Arc: 58, HellaSwag: 81.2, MMLU: 65.2, TruthfulQA: 48.7, WinoGrande: 83.8, GSM8K: 63.

Arxiv:2403.17297 Custom code Internlm2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/internlm/internlm2-7b

Internlm2 7B Benchmarks

IFEval: 22.8 vs 88 (so35)^-74.1%

ARC: 58.02 vs 96.7 (so35)^-40%

HellaSwag: 81.24 vs 95.3 (gpt4)^-14.8%

MMLU: 65.24 vs 88.3 (so35)^-26.1%

TruthfulQA: 48.73 vs 59 (gpt4)^-17.4%

WinoGrande: 83.82 vs 87.5 (gpt4)^-4.2%

GSM8K: 63 vs 96.4 (so35)^-34.6%

MATH Lvl 5: 8.57

LLME Score: 0.22666

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Internlm2 7B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

academic research, commercial applications

Limitations:

Bias, discrimination, harmful content

Additional Notes

InternLM2 is designed for ultra-large context handling and is aligned with conversational use cases via RLHF optimizations.

Input Output

Input Format:

Text

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Using a GPU and loading the model in float16 is recommended for better performance and to prevent OOM errors.

Release Notes

Version:

InternLM2-7B

Date:

2024

Notes:

Release of InternLM2 models with improved capabilities over the previous generation.

Version:

InternLM2-20B

Date:

2024

Notes:

Enhanced version with advanced reasoning and domain-specific corpus pretraining.

LLM Name	Internlm2 7B
Repository 🤗	https://huggingface.co/internlm/internlm2-7b
Model Size	7b
Required VRAM	15.5 GB
Updated	2026-04-23
Maintainer	internlm
Model Type	internlm2
Model Files	10.0 GB: 1-of-2 5.5 GB: 2-of-2
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

Quantized Models of the Internlm2 7B

Model	Likes	Downloads	VRAM
...rnlm2 20B Llama 4.0bpw H6 EXL2	1	1	11 GB

Best Alternatives to Internlm2 7B

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 7B	256K / 15.5 GB	3039	18
Internlm2 5 7B Chat 1M	256K / 15.4 GB	1005	72
Internlm2 5 7B Chat	32K / 15.4 GB	42348	200
Internlm2 Chat 7B	32K / 15.4 GB	46960	83
Internlm2 Base 7B	32K / 15.5 GB	20062	10
ChemLLM 7B Chat 1 5 SFT	32K / 15.4 GB	31	5
MD Judge V0.2 Internlm2 7b	32K / 15.4 GB	554	17
...nternlm2 5 7B Chat Abliterated	32K / 15.4 GB	149	2
GouMang	32K / 15.4 GB	7	0
Internlm2 Chat 7B Sft	32K / 15.4 GB	3347	6

Note: green Score (e.g. "73.2") means that the model is better than internlm/internlm2-7b.

Rank the Internlm2 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53472 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Internlm2 7B by internlm