Qwen3-Embedding-4B-TQ4_1S-GGUF

  • Original model: Qwen/Qwen3-Embedding-4B
  • Quantization: TQ4_1S (TurboQuant, ~5.0 bpw, WHT-rotated)
  • Size: ~2.5 GB (from 7.5 GB f16)
  • GGUF backend: llama.cpp TQP v0.2.0 (TurboQuant Plus)

Качество сопоставимо с Q8_0 при вдвое меньшем размере. Сделано через TurboQuant Plus.

Использование

llama.cpp / TurboQuant

llama-server --embedding -m Qwen3-Embedding-4B-TQ4_1S.gguf -ngl 99

LocalAI

Создать /usr/share/localai/models/qwen3-embedding.yaml:

name: qwen3-embedding
backend: llama-cpp
files:
  - filename: Qwen3-Embedding-4B-TQ4_1S.gguf
    uri: huggingface://grevinden/Qwen3-Embedding-4B-TQ4_1S-GGUF/Qwen3-Embedding-4B-TQ4_1S.gguf

После этого перезапустить LocalAI — модель подтянется автоматически.

OpenAI-compatible API

curl http://localhost:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello world",
    "model": "qwen3-embedding"
  }'

HuggingFace Hub (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="grevinden/Qwen3-Embedding-4B-TQ4_1S-GGUF",
    filename="Qwen3-Embedding-4B-TQ4_1S.gguf",
    embedding=True,
)
embeddings = llm.create_embedding("Hello world")

Характеристики модели

Параметр Значение
Hidden size 2560
Layers 35
Attention heads 20
Max tokens 32768
Embedding dim 2560
Pooling cls
GGUF type TQ4_1S (5.15 BPW)
Размер файла ~2.5 GB
Downloads last month
215
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support