Get the latest setups
Models/WeMM Embedding 2B
Text / tencent

WeMM Embedding 2B

WeMM-Embedding-2B is an Apache-2.0 licensed multimodal embedding model from Tencent, built on Qwen/Qwen3.5-2B. It is intended for feature extraction and produces a 2,048-dimensional L2-normalized embedding. It accepts text, images, videos, visual documents, and interleaved multimodal inputs, but does not support audio input. It is associated with sentence-transformers, multimodal/text/image/video embedding, and MRL tags, and lists Chinese and English language support. Usage examples are provided for Transformers and Sentence Transformers, including encoding text, image, and video inputs independently or in combination.

EstimatedRepository opened Aug 25, 2026Source checked 9/23/2026Version: bbd6cd4b
LOCALRENTED GPUOPEN WEIGHTS
Freshness 75 out of 100. Repository age: 75 days old, Aug 25, 2026. Measures age, not quality.
Popularity 56 out of 100. 13,706 downloads in 30 days; 125 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Nov 8, 2026. Statistics checked Nov 7, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
2.72B
Architecture
qwen3_5
License
apache-2.0
Disk space
5.1 GB
Software
SGLang, vLLM
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Extracting embeddings for text inputs.
  • Extracting embeddings for image inputs.
  • Extracting embeddings for video inputs.
  • Extracting embeddings for visual documents.
  • Extracting embeddings for interleaved multimodal inputs containing combinations of text, images, and videos.

Tradeoffs

  • Audio input is not supported.
  • The source data does not establish compatibility beyond the stated libraries, versions, or example code.
  • The source data does not specify performance characteristics or benchmark results.
  • The source data does not specify numerical hardware requirements beyond the example using CUDA.
  • The source data does not state license terms beyond the provided Apache-2.0 identifier and license link.

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

python -m sglang.launch_server --model-path "$MODEL_PATH" --is-embedding --enable-precise-embedding-interpolation
Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve "$MODEL_PATH" --runner pooling --chat-template "$MODEL_PATH/embedding_chat_template.jinja"
Official instructions

Explore its uses

SAFETENSORSFEATURE-EXTRACTION

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.
Popularity 85 out of 100. 1,710,588 downloads in 30 days; 2,952 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

An open-weight model for reasoning, coding, agents, and image understanding. DeepSeek V4.1 Flash combines a 552B backbone with sparse activation and up to one million tokens of context. Choose the original checkpoint or a community uncensored variant below.

Freshness 80 out of 100. Repository age: 59 days old, Sep 10, 2026. Measures age, not quality.
Popularity 87 out of 100. 1,911,780 downloads in 30 days; 4,887 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
MODEL SIZE552B backbone · 8B active prefill / 16B active decode
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →
WeMM Embedding 2B: hardware, VRAM & setup | YouRunAI