We value your privacy

We use cookies to enhance your browsing experience, serve personalized content and analyze our traffic. By clicking “Accept all” you consent to our use of cookies. Cookie Policy

More options
Skip to content
FacthoryFacthory
FacthoryFacthory
    • Workspace
    • Agent
    • Knowledge
    • Analytics
    • Office apps
    • Desktop
    All features
    What’s new
    Download
  • By work

    • Organizational Knowledge Risk & Gap Intelligence
    • Scientific Research & Experimentation
    • Autonomous Analytics & Insight Discovery
    • Workforce Readiness & Adaptive Learning
    • SOP Governance & Operational Standardization
    • Process Discovery & Continuous Optimization
    • All solutions

    By industry

    • Manufacturing
    • Automotive
    • Construction & Infrastructure
    • Real Estate
    • Public Sector
    • Life Sciences
    • All industries
  • Facthory for

    • Regulated industries
    • On-premises
    • Developers

    Discover

    • What’s new
    • Blog
    • Case studies
    • Webinars
    • Models

    Learn

    • Documentation
    • Help centre
  • Pricing
  • Download
Sign inGet started

A workspace for what your organization knows, with an agent that works on it.

Product

  • All features
  • Workspace
  • Agent
  • Knowledge
  • Analytics
  • Office apps
  • Desktop
  • Download
  • Pricing

Solutions

  • Organizational Knowledge Risk & Gap Intelligence
  • Scientific Research & Experimentation
  • Autonomous Analytics & Insight Discovery
  • Workforce Readiness & Adaptive Learning
  • SOP Governance & Operational Standardization
  • Process Discovery & Continuous Optimization
  • All solutions
  • All industries

Resources

  • Blog
  • Case studies
  • Webinars
  • Documentation
  • Help centre
  • Models
  • ROI calculator

Company

  • Who we are
  • Careers
  • Press hub
  • Brand kit
  • Philosophy
  • Contact us

Join our newsletter

Product news from Facthory, by email.

​

© 2026 Facthory. All rights reserved.
  • Privacy policy
  • Cookie policy
  • Terms and conditions
  • Imprint
  • Cookie settings
All modelstencent

WeMM-Embedding-9B

feature-extraction
9.4B parameters
other
No file flagged

WeMM-Embedding-9B is a universal multimodal embedding model built on Qwen3.5 that accepts text, images, videos, visual documents, and interleaved multimodal inputs, and returns a 4,096-dimensional L2-normalized embedding.

View on Hugging FaceCompare with other models

Fact sheet

Parameters

9.4B

Context length

262,144 tokens

Architecture

Qwen3_5ForConditionalGeneration

Shape

32 layers, hidden size 4,096, 16 attention heads, 4 key-value heads

Weights stored as

bfloat16

Task

feature-extraction

Languages

zh, en

Built on

Qwen/Qwen3.5-9B

Released

25 Aug 2026

Last updated

3 Sept 2026

Downloads (last 30 days)

2,899

Licence and access

Licence

other (apache-2.0) · Read the licence

Access

Weights download without approval

Security

Hugging Face security scan

No file flagged

Weight files by format

Safetensors: 1
Pickle-based: 0
GGUF: 0
Other formats: 0
Pickle-based files (.bin, .pt, .pth, .pkl, .ckpt) can run code when they are loaded; safetensors files cannot.

Facthory’s checks

Automated
Met
Safe weight formats

Every weight file is safetensors or GGUF.

Met
The hub’s malware and pickle scan

No file flagged.

Met
A declared licence

The card declares its licence.

Not evidenced
Published safety evaluations

The card reports no safety evaluation.

GPU calculator

How much memory this model needs to serve at a quantization, context and number of concurrent sequences, which GPUs hold it, and how fast it can generate. Estimates from the model’s published size and shape, with the assumptions below.

Weights

BF16 / FP16 (16 bit)
​

Context per sequence: 8K tokens

Concurrent sequences: 1

KV cache

Memory

22 GB

Weights: 19 GB

KV cache: 1.1 GB

Runtime: 2 GB

GPUMemoryGPUs neededPer sequenceAll sequences
NVIDIA L424 GB
2 ×
18 tokens/s18 tokens/s
NVIDIA L40S48 GB
1 ×
26 tokens/s26 tokens/s
NVIDIA RTX 6000 Ada48 GB
1 ×
29 tokens/s29 tokens/s
NVIDIA RTX PRO 6000 Blackwell96 GB
1 ×
54 tokens/s54 tokens/s
NVIDIA A100 80GB SXM80 GB
1 ×
62 tokens/s62 tokens/s
NVIDIA H100 SXM80 GB
1 ×
101 tokens/s101 tokens/s
NVIDIA H200 SXM141 GB
1 ×
145 tokens/s145 tokens/s
AMD Instinct MI300X192 GB
1 ×
160 tokens/s160 tokens/s
AMD Instinct MI325X256 GB
1 ×
181 tokens/s181 tokens/s
Assumptions
  • Runtime memory (activations, buffers) is 10% of weights and KV cache, plus 1 GB per GPU for the framework.
  • A GPU is filled to at most 90% of its memory; tensor parallelism uses 1, 2, 4 or 8 GPUs in one server.
  • Generation is limited by memory bandwidth at 60% of the vendor’s peak: each step reads the weights once and every sequence’s KV cache. A mixture-of-experts model reads only its active experts, so it runs faster than shown.
  • GPU memory and bandwidth are the vendors’ published figures.

Profile

Kind

Embedding model

Lineage

Fine-tune

Family

Qwen3.5

Uses

Image generation
Video generation

In and out

Text, Image, Video → Embedding

Written on 10 Nov 2026 by Workers AI (@cf/zai-org/glm-4.7-flash) from the model card and the hub’s metadata: a reading of the publisher’s text, not checked by Facthory.

Published benchmarks

The model card publishes no benchmark results.

EU AI Act

What the EU AI Act asks of a general-purpose AI model depends on who places it on the EU market and how. These facts bear on it:

  • Licence: other
  • Access: Weights download without approval
  • Parameters: 9.4B
Automated
Rated by Facthory’s crawler from the published facts; a person has not reviewed it yet.

General-purpose AI model (Article 3(63))

Not indicated. Its task (feature-extraction) generates no text, audio, images or video, which the Commission’s indicative criterion asks for.

Articles 51 to 55, the obligations for general-purpose AI models, do not bind its provider.

Regulation (EU) 2024/1689, the EU AI Act · Source: General-Purpose AI Code of Practice, read 8 Nov 2026

Facthory’s EU AI Act score appears once a person has reviewed these checks. The articles we score against

Source: Read from Hugging Face on 17 Nov 2026, at commit 00c5283. huggingface.co/tencent/WeMM-Embedding-9B
Rated by Facthory’s crawler from the published facts; a person has not reviewed it yet. How we rate