What are the hardware requirements for MMedLM2 1 8B?

MMedLM2 1 8B requires approximately 7.6 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 MMedLM2 1 8B and how large is it?

MMedLM2 1 8B is developed by Henrychur, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate MMedLM2 1 8B?

MMedLM2 1 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MMedLM2 1 8B by Henrychur — VRAM 7.6GB, 32K context

Name: MMedLM2 1 8B
Author: Henrychur

MMedLM2 1 8B is an open-source language model by Henrychur. Features: 8b LLM, VRAM: 7.6GB, Context: 32K, License: cc-by-4.0, LLM Explorer Score: 0.11.

Arxiv:2402.13963 Custom code Dataset:henrychur/mmedc En Es Feature-extraction Fr Internlm2 Ja Medical Region:us Ru Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/Henrychur/MMedLM2-1_8B

MMedLM2 1 8B Parameters and Internals

Model Type

Multilingual, Medical, Auto-regressive

Use Cases

Areas:

Medical domain research and applications

Applications:

Multilingual medical language processing

Primary Use Cases:

Multilingual medical text analysis

Additional Notes

Foundation model not instruction fine-tuned yet.

Supported Languages

languages_supported_and_proficiency_levels (English, Chinese, Japanese, French, Russian, Spanish)

Training Details

Data Sources:

MMedC

Data Volume:

25.5B tokens

Methodology:

Auto-regressive pretraining

Context Length:

2048

Hardware Used:

GPU

Model Architecture:

Foundation model based on InternLM with further training on MMedC

Input Output

Input Format:

Tokenized input with predefined tokenizer

Accepted Modalities:

Text

Output Format:

Textual output

Performance Tips:

Ensure using suggested tokenizer and torch float16

Release Notes

Version:

2-1.8B

Date:

2024-02-21

Notes:

Released preprint paper and model

LLM Name	MMedLM2 1 8B
Repository 🤗	https://huggingface.co/Henrychur/MMedLM2-1_8B
Model Size	8b
Required VRAM	7.6 GB
Updated	2026-08-03
Maintainer	Henrychur
Model Type	internlm2
Model Files	5.0 GB: 1-of-2 2.6 GB: 2-of-2
Supported Languages	en zh ja fr ru es
Model Architecture	InternLM2ForCausalLM
License	cc-by-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.0
Is Biased	0
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Vocabulary Size	92544
Torch Data Type	float32

Rank the MMedLM2 1 8B 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 MMedLM2 1 8B

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 1 8b Chat	32K / 3.8 GB	1470	26
Internlm2 Chat 1 8b	32K / 3.8 GB	5801	36
Internlm2 1 8b	32K / 3.8 GB	5485	32
Internlm2 5 1 8b	32K / 3.8 GB	245	25
Internlm2 Chat 1 8b ExPO	32K / 3.8 GB	7	1
...ternlm2 Chat 1 8b Ultracabrita	32K / 3.8 GB	6	0
Internlm2 Chat 1 8b Sft	32K / 3.8 GB	226	9
Internlm2 Math Plus 1 8b	8K / 3.8 GB	663	12

Note: green Score (e.g. "73.2") means that the model is better than Henrychur/MMedLM2-1_8B.