WE

WeMM Embedding 2B

WemmGGUF by ewin-regUpdated 2026-09-08
Download on Hugging Face
Parameters2.39B
Context256K
Layers25
Architectureqwen35
Smallest quant1.6 GB
Quick answer

WeMM Embedding 2B needs about 2.5 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.6 GB (Q4_K_M) to 2.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

WeMM Embedding 2B – 2.39B parameter multimodal embedding model

WeMM Embedding 2B is a 2.39‑billion parameter hybrid linear‑attention model built on Qwen3.5. It generates 2,048‑dimensional L2‑normalized embeddings for text, images, videos, and visual documents. The model is licensed under Apache‑2.0.

Good at

  • Text, image, and video embedding
  • Code search and retrieval
  • High‑throughput RAG backend

Limits

  • No audio input support
  • Requires 8k context for memory estimates
  • No vision support in some frameworks

Best for

  • Code search engines
  • Vector database indexing
  • RAG pipelines for technical content

Who it’s for. Developers building semantic search over codebases or multimodal content. Researchers needing dense embeddings for large‑scale retrieval tasks. Teams integrating embeddings into vector databases or RAG systems.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.6 GB 2.5 GB
Fits Get file →
—1.6 GB 2.5 GB
Fits Get file →
—1.6 GB 2.5 GB
Fits Get file →
Q5_K_M1.8 GB 2.7 GB
Fits Get file →
Q6_K2.0 GB 2.9 GB
Fits Get file →
Q8_02.6 GB 3.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.56 GB file, ~2.5 GB RAM). For 12 GB VRAM, Q5_K_M (1.76 GB file, ~2.7 GB RAM). For 16 GB VRAM, Q6_K (1.97 GB file, ~2.9 GB RAM).

What GPU do you need for WeMM Embedding 2B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (2.6 GB file, about 3.5 GB in use).

Which WeMM Embedding 2B quant should you choose?

Q4_K_M is the usual starting point for WeMM Embedding 2B: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 2.6 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters2.39B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized byewin-reg
FamilyWemm
Licenseapache-2.0
Downloads (HF)657
Last updated2026-09-08

Frequently asked questions about WeMM Embedding 2B

How much VRAM does WeMM Embedding 2B need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run WeMM Embedding 2B on an 8 GB GPU?

Yes, with Q8_0: the 2.6 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WeMM Embedding 2B GGUF?

It depends on the quant: Q4_K_M is 1.6 GB, file is 1.6 GB, file is 1.6 GB, Q5_K_M is 1.8 GB, Q6_K is 2.0 GB, Q8_0 is 2.6 GB.

What context length does WeMM Embedding 2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download WeMM Embedding 2B GGUF?

The files are on Hugging Face in the ewin-reg/WeMM-Embedding-2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does WeMM Embedding 2B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run WeMM Embedding 2B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 2.5 GB of RAM, which fits within 8 GB VRAM when using llama.cpp.

Does this model support audio input?

No, audio input is not supported by WeMM Embedding 2B.

What license applies to the model?

The model is released under the Apache‑2.0 license.

Other GGUFs of WeMM-Embedding-2B

Similar models

Browse all →

More from ewin-reg

All by ewin-reg →

More Wemm models

All Wemm →

Other tiny models

All tiny models →