majentik/Qwen3-Embedding-0.6B-GGUF-IQ4_XS

Qwen3-Embedding-0.6B GGUF IQ4_XS

llama.cpp GGUF IQ4_XS quantization of Qwen/Qwen3-Embedding-0.6B.

• —Produced with: llama-quantize (upstream llama.cpp, April 2026 build)
• —BF16 source converted via convert_hf_to_gguf.py from the fresh llama.cpp tree
• —Quant type: IQ4_XS
• —File size: 352 MB

Quickstart

llama-embedding -m qwen3-emb-0.6b-IQ4_XS.gguf \
  -p "What is the capital of France?"

Or via llama-cpp-python:

from llama_cpp import Llama
llm = Llama(model_path="qwen3-emb-0.6b-IQ4_XS.gguf", embedding=True)
vec = llm.embed("What is the capital of France?")

License

Apache 2.0 — inherited from the upstream base model.

See also

• —Base: Qwen/Qwen3-Embedding-0.6B
• —Garden hub: majentik/garden
• —llama.cpp: https://github.com/ggml-org/llama.cpp