What are the hardware requirements for MLExpert?

MLExpert requires approximately 69.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MLExpert and how large is it?

MLExpert is developed by InternScience, a model with 34.7b 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 MLExpert?

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

MLExpert by InternScience — VRAM 69.7GB

Name: MLExpert
Author: InternScience

MLExpert is an open-source language model by InternScience. Features: 34.7b LLM, VRAM: 69.7GB, License: apache-2.0, LLM Explorer Score: 0.32.

Arxiv:2610.22344 Agentic Code Conversational Endpoints compatible Image-text-to-text Machine-learning-engineering Moe Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Tool-use

Model Card on HF 🤗: https://huggingface.co/InternScience/MLExpert

MLExpert Parameters and Internals

LLM Name	MLExpert
Repository 🤗	https://huggingface.co/InternScience/MLExpert
Model Size	34.7b
Required VRAM	69.7 GB
Updated	2026-10-21
Maintainer	InternScience
Model Type	qwen3_5_moe
Model Files	5.4 GB: 0-of-13 5.4 GB: 1-of-13 5.4 GB: 2-of-13 5.4 GB: 3-of-13 5.4 GB: 4-of-13 5.4 GB: 5-of-13 5.4 GB: 6-of-13 5.4 GB: 7-of-13 5.4 GB: 8-of-13 5.4 GB: 9-of-13 5.4 GB: 10-of-13 5.4 GB: 11-of-13 4.9 GB: 12-of-13
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the MLExpert 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 MLExpert

Best Alternatives	Context / RAM	Downloads	Likes
Edge0 35B A3B Preview	0K / 19.6 GB	951	98
Affine 5dfqbbh8ev Sft	0K / 69.3 GB	388	0
5eqdtdzqle Ckpt1000 M7	0K / 71.7 GB	22	0
Nex N2.5 Mini MLX 4bit	0K / 19.5 GB	1077	6
Occamy 1.0 MLX 4bit	0K / 19.5 GB	739	2
Nex N2.5 Mini OptiQ 4bit	0K / 22.2 GB	282	2
Agents A1 OptiQ 4bit	0K / 22.2 GB	891	3
...CybersecurityLLM V1.0 Mlx 4Bit	0K / 19.5 GB	765	47
KAT Coder V2.5 Dev OptiQ 4bit	0K / 21.9 GB	114	3
XYZ Aquila Mini OptiQ 4bit	0K / 36.3 GB	34	3

Note: green Score (e.g. "73.2") means that the model is better than InternScience/MLExpert.