Skip to content

Nicolassuez

Qwen3-Embedding-0.6B-W8A16-g128-resident

Nicolassuez/Qwen3-Embedding-0.6B-W8A16-g128-resident

Qwen3-Embedding-0.6B-W8A16-g128-resident is a feature extraction model from Nicolassuez. Use it when you need embeddings to search or compare text. The card lists the license as apache-2.0.

Same int8 weight-only groupsize-128 quantization as Qwen3-Embedding-0.6B-W8A16-g128, but packaged as repo custom code (trustremotecode=True) whose Int8GroupLinear modules keep the int8 weights RESIDENT in VRAM and deq…

Downloads · 30 days

3

1% of all-time downloads

All-time downloads

297

Public

Parameters

599M

1.4 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors603 MB · 98%

Parameter types

How the weights are stored.

I8596M · 99%

Base models

Task
Feature Extraction
Type
qwen3
License
apache-2.0
Languages
multilingual
Created
Jul 27, 2026
Updated
Jul 27, 2026