Model reference · open weights

Qwen3-Embedding-G128

Qwen3-Embedding-G128 is an open-weight embedding model from boboliu, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings boboliu 1 variants 542k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Qwen3-Embedding-G128 is

Qwen3-Embedding-4B-W4A16-G128 GPTQ Quantized Qwen/Qwen3-Embedding-4B with THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set. What's the benefit? VRAM Usage: 17430M - 11000M (w/o FA2). What's the cost? ~0.72% lost in C-MTEB. Evaluation performed with official code. How to use it? pip install compressed-tensors optimum and auto-gptq / gptqmodel, then goto the official usage guide.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerboboliu
TypeEmbedding models
Parameters (lead)4.1B
Context40k tokens
Variants1
Runs withsentence-transformers
Based onQwen/Qwen3-Embedding-4B
Released2025-06-06
Popularity542k downloads / month
Likes5
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Qwen3-Embedding-4B-W4A16-G1284.1BBF16~9.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys qwen3-embedding-g128 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-embedding-g128 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-embedding-g128","input":"text to embed"}'

Details

Languages, data & research

Tags

sentence-transformers safetensors qwen3 text-generation transformers sentence-similarity feature-extraction text-embeddings-inference endpoints_compatible compressed-tensors

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Qwen3-Embedding-G128 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms