AX-Nemotron-3-Embed-8B-MLX-AXQ-6bit

AX-Nemotron-3-Embed-8B-MLX-AXQ-6bit

Research development artifact. Base affine6 packing with higher-precision protection, not MXFP6 or uniformly six-bit storage. No quality certificate is issued.

The precision distribution and exact per-module settings are recorded in axquant_manifest.json, axquant_plan.json, and config.json. Complete BPW includes protected tensors and storage overhead. File size does not establish peak runtime memory requirements. Converted from the pinned original source with existing precision protection floors.

Observed runtime evidence

The exact runtime payload passed the following scoped check on Metal. The receipt binds its runtime input files. This is a functional smoke, not a quality benchmark, MTEB evaluation, coding evaluation, long-context test or MTP acceleration result.

{
  "task": "embedding",
  "runtime": "mlx-vlm",
  "version": "0.7.9",
  "mlx_version": "0.32.4",
  "cases": [
    {
      "finite": true,
      "mars_ranks_above_venus": true,
      "min_cosine_vs_source": 0.9991735219955444,
      "passed": true,
      "shape": [
        3,
        4096
      ],
      "unit_norm": true
    }
  ]
}

Unexercised modalities and MTP behavior remain unverified. Peer runtime-specific exports require distinct variants and their own testing. See the manifest-bound static report.

Use and provenance

python -m pip install -U huggingface_hub mlx-vlm
hf download AutomatosX/AX-Nemotron-3-Embed-8B-MLX-AXQ-6bit --local-dir ./AX-Nemotron-3-Embed-8B-MLX-AXQ-6bit

Pin the immutable Hub revision. Use mlx_vlm.embedding_loader.load_embedding_model for embeddings, preserving source pooling and task prefixes. The source license and notices are retained where supplied. The upstream repository and its license govern downstream use; no additional commercial grant or upstream benchmark/certification transfer is implied.