What are the hardware requirements for Internlm2 5 20B Chat?

Internlm2 5 20B Chat 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 5 20B Chat and how large is it?

Internlm2 5 20B Chat 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 5 20B Chat perform on standard benchmarks?

Internlm2 5 20B Chat has the following published scores: LMSYS ELO 1191. Compare against reference models on this page or on the LLM Explorer leaderboards.

Internlm2 5 20B Chat by internlm — VRAM 39.7GB, 32K context

Name: Internlm2 5 20B Chat
Author: internlm

Internlm2 5 20B Chat is an open-source language model by internlm. Features: 20b LLM, VRAM: 39.7GB, Context: 32K, License: other, LLM Explorer Score: 0.4, ELO: 1191.

Arxiv:2403.17297 Conversational Custom code Feature-extraction Internlm2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/internlm/internlm2_5-20b-chat

Internlm2 5 20B Chat Benchmarks

LMSys ELO 1191 vs 1272 (so35) -6.4%

^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)

Internlm2 5 20B Chat Parameters and Internals

Model Type

text generation, chat

Use Cases

Areas:

academic research, commercial applications

Primary Use Cases:

Chat applications, Instruction following, Tool selection and reflection

Limitations:

Model may generate biased or harmful content

Additional Notes

Model weights are open for academic use and can be used for free commercial applications with a license application.

Input Output

Input Format:

Supports textual input in both English and Chinese.

Accepted Modalities:

text

Output Format:

Textual responses

LLM Name	Internlm2 5 20B Chat
Repository 🤗	https://huggingface.co/internlm/internlm2_5-20b-chat
Model Size	20b
Required VRAM	39.7 GB
Updated	2026-08-03
Maintainer	internlm
Model Type	internlm2
Model Files	1.9 GB: 1-of-21 1.9 GB: 2-of-21 2.0 GB: 3-of-21 1.9 GB: 4-of-21 2.0 GB: 5-of-21 1.9 GB: 6-of-21 2.0 GB: 7-of-21 1.9 GB: 8-of-21 2.0 GB: 9-of-21 1.9 GB: 10-of-21 2.0 GB: 11-of-21 1.9 GB: 12-of-21 2.0 GB: 13-of-21 1.9 GB: 14-of-21 2.0 GB: 15-of-21 1.9 GB: 16-of-21 2.0 GB: 17-of-21 1.9 GB: 18-of-21 2.0 GB: 19-of-21 1.6 GB: 20-of-21 1.1 GB: 21-of-21
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 5 20B Chat 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 5 20B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 20B	256K / 39.7 GB	158	17
Internlm2 Chat 20B ExPO	32K / 39.8 GB	15821	1
Internlm2 20B	32K / 39.7 GB	20503	59
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