AX Qwen3 Embedding 0.6B MLX 8-bit

Parameter count: approximately 595.78M logical parameters (0.6B class). 8-bit is the quantization precision, not the model size.

This is an MLX text-embedding model for Apple Silicon. The weight tensor payload, configuration, and tokenizer are byte-identical to mlx-community/Qwen3-Embedding-0.6B-8bit at revision 407ad2329cd30702720aafe83f74a1ba30fdfbca.

AutomatosX adds an AX Engine native manifest, pinned provenance, tested serving instructions, and this model card. Only Safetensors header metadata was added to report the logical parameter count to the Hub; tensor payload bytes were not changed or re-quantized. This is an embedding-only release and does not use MTP.

Model details

• Base model: Qwen/Qwen3-Embedding-0.6B
• Format: MLX Safetensors
• Quantization: 8-bit, group size 64
• Embedding dimension: 1,024
• Transformer layers: 28
• Configured context length: 32,768 tokens
• Intended hardware: Apple Silicon

Download

hf download AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-8bit \
  --local-dir ./AX-Qwen3-Embedding-0.6B-MLX-8bit

Serve with AX Engine

Install AX Engine, then serve the downloaded directory:

ax-engine serve ./AX-Qwen3-Embedding-0.6B-MLX-8bit \
  --port 31418 -- --model-id qwen3

Create full-size normalized embeddings:

curl http://127.0.0.1:31418/v1/embeddings \
  -H 'Content-Type: application/json' \
  --data '{
    "model": "qwen3",
    "input": [
      "Instruct: Find passages that answer this query.\nQuery: What is the capital of Canada?",
      "Ottawa is the capital city of Canada."
    ],
    "encoding_format": "float",
    "pooling": "last",
    "normalize": true
  }'

For text inputs, AX Engine appends the configured EOS token before last-token pooling. Add an English task instruction to retrieval queries when useful; documents normally remain unprefixed. The endpoint returns 1,024-dimensional vectors. Do not pass the OpenAI dimensions field to this AX Engine version.

Validation and provenance

The release was validated on macOS arm64 with AX Engine 6.9.0:

• AX native artifact validation: ready, with no issues
• Live POST /v1/embeddings batch: passed
• Returned dimensions: 1,024
• L2-normalized vector norms: approximately 1.0
• Upstream tensor payload, configuration, tokenizer, and Sentence Transformers assets: byte-exact; the Safetensors header and shard index add only the corrected logical parameter count

See ax_provenance.json for pinned source and SHA-256 values.

License

Apache License 2.0. See LICENSE and the upstream Qwen model card for model limitations and responsible-use guidance.