Conversion and optimization toolkit
Convert and optimize your model for iPhone, iPad and Mac.
Convert and optimize your model for Apple devices.
Conversion and optimization toolkit
Conversion and optimization toolkit
One command to get your model running on 2B Apple devices.
One command to get your model running on 2 billion Apple devices.
For popular architectures
Convert in one command.
If your model is based on a popular architecture, including your own fine-tunes and adaptations, it converts in one command.
Out of the box converter for popular model families.
Fine-tunes and adaptations supported.
Automatically fetches models from HF and converts them.
For popular architectures
Convert in one command.
If your model is based on a popular architecture, including your own fine-tunes and adaptations, it converts in one command.
Out of the box converter for popular model families.
Fine-tunes and adaptations supported.
Automatically fetches models from HF and converts them.
For custom architectures
Add new architectures easily.
If your model uses standard blocks, adding support is just a new config. If it uses custom layers, we build the converter for you.
Config-based architecture support.
Custom layers handled by our team.
Same optimization, validation pipeline as popular architectures.
For custom architectures
Add new architectures easily.
If your model uses standard blocks, adding support is just a new config. If it uses custom layers, we build the converter for you.
Config-based architecture support.
Custom layers handled by our team.
Same optimization, validation pipeline as popular architectures.
def to_decoder_config(self,context_length: int | None,activation_precision: DTypeLike,accumulation_precision: DTypeLike,metadata_dict: Mapping[str, str], # noqa: ARG002) -> DecoderConfig:if self.tie_word_embeddings:embedding_config = TiedEmbeddingConfig(input_scale=None,logit_soft_cap=None,precision=activation_precision,)else:embedding_config = UntiedEmbeddingConfig(input_scale=None,logit_soft_cap=None,precision=activation_precision,)rope_config = UnscaledRoPEConfig(precision=activation_precision,base=self.rope_theta,max_sequence_length=context_length or self.max_position_embeddings,)
Mirai can support your custom / non-standard layers.
We will build full conversion pipeline specifically for your model. You will have the same correctness validation and quality measurement as standard models.
Mirai can support your custom / non-standard layers.
We will build full conversion pipeline specifically for your model. You will have the same correctness validation and quality measurement as standard models.
Our optimization pipeline prepares your model for peak performance on Apple devices.
Draft model training for speculative decoding.
Draft model training for speculative decoding.
Layer fusion and weight optimization.
We train a lightweight draft model matched to yours. The draft predicts tokens ahead, your model verifies in one pass. Up to 2x faster generation.
Quantization with minimal quality loss.
Quantization with minimal quality loss.
We use state of the art quantization methods to achieve the best quality at the given size. You see the exact tradeoff between size, speed, and accuracy.
Output correctness and quality validation.
Output correctness and quality validation.
Output correctness and quality validation.
Layer-by-layer comparison against reference outputs. We measure how optimization affects your model's output quality. Any deviation is flagged.
Models already running on Mirai.
Optimize your model for 2 billion Apple devices. Perfect for:
Model companies.
You train and ship models. Mirai optimizes them for Apple Silicon, benchmarks on real hardware, and distributes.
AI researchers & labs.
Mirai converts your model and puts it in front of real users on Apple devices, not just leaderboards.
Independent makers.
You're fine-tuning or training from scratch. Mirai gives your model the same device reach as OpenAI and DeepSeek.
Model companies.
You train and ship models. Mirai optimizes them for Apple Silicon, benchmarks on real hardware, and distributes.
AI researchers & labs.
Mirai converts your model and puts it in front of real users on Apple devices, not just leaderboards.
Independent makers.
You're fine-tuning or training from scratch. Mirai gives your model the same device reach as OpenAI and DeepSeek.
Common questions:
How does model support work?
How does model support work?
What architectures are supported?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
What architectures are supported?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How does Mirai compare to other inference engines?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How does Mirai compare to other inference engines?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
What is the maximum supported model size?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
What is the maximum supported model size?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How can I run benchmarks myself?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How can I run benchmarks myself?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How can we discuss a specific use case?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
How can we discuss a specific use case?
Framer is a design tool that allows you to design websites on a freeform canvas, and then publish them as websites with a single click.
