Why only 6bit? Protection floors lift the low-memory plan to ~5.99 BPW, essentially the same as this ~6.00 BPW pack (~6.7 GB). A separate AXQ-4bit sibling would not save memory — use this pack only.

AX-Ministral-3-8B-Instruct-2512-MLX-AXQ-6bit

An AXQuant (AXQ) mixed-precision MLX checkpoint for Apple Silicon, converted directly from the BF16 source model. The language path is quantized while the vision tower are preserved as BF16 sidecars when present.

Development evidence — not a certified AXQuant release. This package has conversion and artifact-integrity records, but it does not publish measured quality, long-context, kernel-speed, or MTP-speed evidence. Do not interpret the AXQ product label as a benchmark claim.

Stable-name v2. main serves the audited v2 artifact for backward compatibility. The same revision is tagged v2; the replaced artifact remains recoverable at legacy-pre-v2.

Model details

This repository contains MLX Safetensors. It does not contain PyTorch or GGUF weights.

Why there is no AXQ-4bit pack

On Ministral-3-8B, AXQuant protection floors raise the low-memory (~4.8 BPW) plan to about 5.99 BPW, while the 6bit plan sits at about 6.00 BPW. Download size and layout are nearly the same (~6.7 GB); there is no meaningful size or precision ladder between the two product names.

The former …-AXQ-4bit sibling was retired so users are not offered a false “smaller 4bit” choice. AutomatosX keeps only this repository as the public AXQ pack for this base.

Choosing an AXQ pack

AXQ 4bit / 6bit names are storage-budget product classes, not a promise that every tensor uses that width. On this base there is no distinct 4bit Hub pack — see Why there is no AXQ-4bit pack above.

See the AutomatosX MLX model catalog for related MLX and OptiQ alternatives.

Download

python -m pip install -U huggingface_hub
hf download AutomatosX/AX-Ministral-3-8B-Instruct-2512-MLX-AXQ-6bit --local-dir ./AX-Ministral-3-8B-Instruct-2512-MLX-AXQ-6bit

Allow at least 6.71 GB of free disk space. Pin the resulting Hub commit in reproducible deployments rather than relying indefinitely on main.

Run with MLX-LM

python -m pip install -U mlx-lm
mlx_lm.generate \
  --model AutomatosX/AX-Ministral-3-8B-Instruct-2512-MLX-AXQ-6bit \
  --prompt "Explain mixed-precision quantization in three sentences." \
  --max-tokens 128 \
  --temp 0.0

MLX-LM compatibility covers standard text/backbone inference. It may ignore AXQuant runtime metadata and optional sidecars (vision.safetensors, mtp.safetensors); this command therefore does not establish MTP acceleration or vision-language quality. The artifact records MLX 0.32.0 and MLX-LM 0.31.3 from conversion.

AX Engine status

This package does not include a validated native model-manifest.json, so AX Engine execution is not established by this release. The AX Engine fields in axquant_runtime.json describe the intended compatibility contract, not observed runtime evidence. Use the MLX-LM path above for standard text/backbone inference. The artifact records AX Engine version not recorded, but version discovery alone is not a runtime check.

Quantization layout

• Quantization methods: affine, bf16.
• Group sizes used by quantized assignments: 32, 64.
• MTP sidecar: not included.
• Vision sidecar: 222 tensors, 428.47M parameters, 0.86 GB, BF16.
• Optimization scope: text-path.
• Support tier: convertible.

BF16 sidecars, when present, are included in total download size. Their presence does not by itself establish MTP acceleration or vision-language quality.

Evidence and validation status

Intended use and limitations

• Intended for local development and evaluation on Apple Silicon with MLX-compatible runtimes.

• No minimum unified-memory figure is claimed; loadability depends on model size, context length, KV-cache policy, runtime buffers, and other processes using unified memory.

• Architecture-prior allocation is not measured sensitivity. It must not be presented as measured model quality.

• Vision weights are byte-preserved at BF16, but this release does not claim validated VLM quality.

• The configured context window can require substantially more memory as the KV cache grows.

• AX Engine execution is not established because this package has no validated native manifest.

• Upstream capabilities, limitations, biases, and responsible-use guidance still apply.

Provenance and audit files

• axquant_manifest.json: package identity, byte accounting, runtime contract, software versions, and file checksums.
• axquant_plan.json: per-tensor precision decisions and planning evidence.
• axquant_quantizer_execution.json: conversion coverage and fallback records.
• axquant_runtime.json: declared AX Engine and MLX-LM compatibility metadata; runtime checks remain separate evidence.
• axquant_vision_sidecar_manifest.json: protected vision tensor provenance.

All published provenance uses repository-relative paths. Local source paths are stripped before publication. The checkpoint was converted from BF16 rather than re-quantized from an OptiQ artifact. Parallel OptiQ repositories use a different quantizer and should not be assumed to have identical BPW or quality.

License

The checkpoint follows the upstream model license where applicable (often Apache License 2.0). See the mistralai/Ministral-3-8B-Instruct-2512-BF16 model card for license terms, model limitations, and responsible-use guidance.