Runtime format audit (2026-10-06)

No quantization-container correction was needed. This family has no n-gram tensors; no n-gram file or declaration was added. This remote format audit does not grant an oMLX/MTPLX runtime profile or a successful load/generation claim.

See runtime_audit.json for pinned config/index/header bindings, architecture, physical-format findings, and applied corrections. This is development evidence; no quality, MTP exactness, speed, or certification claim is added. Historical evidence stays bound to its original revision.

AX-Unlimited-OCR-3B-MoE-MLX-AXQ-MXFP8

Development AXQuant (AXQ) MXFP8 language MLX pack of baidu/Unlimited-OCR @ 07dea832e22aefee32ad281d4b80551282e1c168.

Language experts/attention/MLP and embeddings at native MXFP8 (group 32, physical repack of unrefined 8-bit allocations); dual vision (CLIP + SAM), projector, norms, MoE routers, and LM head BF16-preserved. Measured total 9.57 BPW.

Converted via MLX-VLM unlimited_ocr from tokimoa/unlimited-ocr-mlx-bf16 @ cd57bdd8d4efa47a2e49c2123550cbd698ff529a, a community MLX BF16 remaster that AutomatosX byte-verified against the upstream weights (592 direct + 6 conv-transpose + 33 packed-expert comparisons, zero differences).

Built with AXQuant 1.9.0 (plan-manual + convert --q-mode mxfp8, --allow-unmeasured). Load smoke: mlx-vlm loads 616 modules. MXFP8 is a physical repacking mode, not a measured planner method.

Claims

Claim Status
AXQuant architecture-prior / development quant Yes
OCR accuracy / document-bench scores Not claimed
Vision optimization No — CLIP + SAM encoders + projector BF16-preserved
Certified release No

Attribution

Base weights © Baidu (MIT). BF16 remaster © tokimoa. Quantization by AXQuant (development).

Downloads last month
150
Safetensors
Model size
3B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

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

Model tree for AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-AXQ-MXFP8

Quantized
(41)
this model

Collections including AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-AXQ-MXFP8