You can deploy this model and start earning money today!

AutomatosX/
AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP

Name: AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP
Availability: InStock

Views

No views yet

AX Gemma 4 26B-A4B IT MLX OptiQ 4-bit Assistant MTP

Parameter count: approximately 25.81B logical target parameters (the 26B-A4B model class), with approximately 4B active per token. 4-bit is the target quantization precision, not a 4B model-size claim. The separately packaged assistant is not included in the target count.

This is a self-contained MLX package for Apple Silicon. It combines the pinned upstream OptiQ MoE target with its paired BF16 Gemma assistant for AX Engine multi-token prediction (MTP) / speculative decoding.

Try this model locally with AX Engine.

Attribution and changes

AutomatosX did not train Gemma 4, create the OptiQ quantization, or train the assistant. The target comes from mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit at revision e0061bda54f72709cf6fa51229530c3b14cd9d7d. The assistant comes from mlx-community/gemma-4-26B-A4B-it-assistant-bf16 at revision cda74908f1dbe7d3dbd3030e66576a7d4094144f.

AutomatosX packaged the pinned target and assistant together, generated native manifests, applied the target tokenizer to the assistant subtree so both sides use identical token IDs, and added the exact-pairing contract. The target and assistant weights themselves are unchanged. The upstream OptiQ card is preserved as UPSTREAM_README.md.

No new training or benchmark results are claimed by AutomatosX.

Package details

Property	Value
Target format	MLX Safetensors
Architecture	Mixture of experts; 26B total / 4B active
Target quantization	OptiQ mixed 4/8-bit, group size 64
OptiQ allocation	79 components at 4-bit; 246 at 8-bit
Achieved target BPW	5.0013
Assistant precision	BF16
Pairing	Exact
Maximum draft depth	1
Configured context	262,144 tokens
Intended hardware	Apple Silicon

Download and serve

bash

hf download AutomatosX/AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP \
  --local-dir ./AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP

ax-engine doctor \
  --mlx-model-artifacts-dir ./AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP

ax-engine serve ./AX-Gemma-4-26B-A4B-IT-MLX-OptiQ-4bit-Assistant-MTP --port 31418

The download is approximately 18 GB. AX Engine reads ax_gemma4_assistant_mtp.json, loads the drafter from assistant/, and uses the target model to verify every accepted token. Do not use assistant/ by itself as a general-purpose chat model.

The server exposes an OpenAI-compatible API. Consult the AX Engine repository for installation and API examples.

Validation and provenance

Validated on macOS arm64 with AX Engine 6.9.0 on 2026-07-20:

AX artifact doctor: ready, with no model issues
Safetensors headers, data bounds, and index mappings: passed
Target weight shards: byte-exact against the pinned OptiQ source
Assistant weight: byte-exact against the pinned assistant source
Pairing contract: exact

See ax_provenance.json for immutable source revisions, transformations, and artifact hashes.

Quantization can change model quality, and speculative-decoding acceptance depends on the workload. Evaluate this package on your own tasks.

License

Apache License 2.0. See LICENSE, the Gemma 4 license page, and the official Google model cards for limitations and responsible-use guidance.