boboliu / feature-extraction updated 1 year ago

Qwen3-Embedding-4B-W4A16-G128

GPTQ Quantized Qwen/Qwen3-Embedding-4B with THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set.

Params
4.1 B
Context
40,960
Downloads 30d
532 K
Likes
5
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days
580 K532 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors i32 2.7 GB 4.0 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 40K ctx 2.7 GB 6.5 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Qwen3ForCausalLM
Parameters
4.1 B
Tensor type
I32
Context length
40,960
Vocabulary
151,665
Layers / heads
36 / 32
Licence
apache-2.0
First seen on the Hub
2025-06-06
Base model
Qwen3-Embedding-4B
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.