What are the hardware requirements for WeMM Embedding 2B?

WeMM Embedding 2B requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed WeMM Embedding 2B and how large is it?

WeMM Embedding 2B is developed by tencent, a model with 2b 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 WeMM Embedding 2B?

WeMM Embedding 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

WeMM Embedding 2B by tencent — VRAM 5.4GB

Name: WeMM Embedding 2B
Author: tencent

WeMM Embedding 2B is an open-source language model by tencent. Features: 2b LLM, VRAM: 5.4GB, License: other, LLM Explorer Score: 0.35.

Arxiv:2608.24053 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-2b Custom code En Endpoints compatible Feature-extraction Image-embedding Image-text-to-text Mrl Multimodal-embedding Qwen3 5 Region:us Safetensors Sentence-transformers Text-embedding Video-embedding Zh

Model Card on HF 🤗: https://huggingface.co/tencent/WeMM-Embedding-2B

WeMM Embedding 2B Parameters and Internals

LLM Name	WeMM Embedding 2B
Repository 🤗	https://huggingface.co/tencent/WeMM-Embedding-2B
Base Model(s)	Qwen/Qwen3.5-2B Qwen/Qwen3.5-2B
Model Size	2b
Required VRAM	5.4 GB
Updated	2026-08-31
Maintainer	tencent
Model Type	qwen3_5
Model Files	5.4 GB
Supported Languages	zh en
Model Architecture	Qwen3_5ForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Errors	replace

Rank the WeMM Embedding 2B 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 WeMM Embedding 2B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 2B	0K / 4.5 GB	2633311	352
Qwen3.5 2B Base	0K / 4.5 GB	809591	82
...e Qwen3.5 2B Decision MLX Bf16	0K / 3.8 GB	2801	2
Qwen3.5 2B	0K / 4.5 GB	103487	18
Qwen3.8 2B Distill	0K / 4.5 GB	2056	24
Intern Decision 2B	0K / 0.1 GB	162	9
Qwen3.5 2B Multiharness RL	0K / 4.4 GB	271	1
Qwen3.8 2B Distill Heretic	0K / 4.4 GB	226	1
Qwen3.8 2B MLX 4.83B	0K / 1.3 GB	281	1
VIC 2B	0K / 1.5 GB	58	1

Note: green Score (e.g. "73.2") means that the model is better than tencent/WeMM-Embedding-2B.