MetalRT
A hand-written inference engine for Apple GPUs that supports LLMs, VLMs, speech-to-speech, and embeddings.
What it does
A hand-written inference engine for Apple GPUs that supports LLMs, VLMs, speech-to-speech, and embeddings.
- Category
- Model hosting and inference
- Public API
- Not offered
- Deployment
- Self-hosted
Not yet disclosed: platforms, languages and support channels.
Pricing
Pricing isn't published
RunAnywhere, Inc. doesn't list prices publicly. Ask them for a quote.
Security and compliance
As reported by RunAnywhere, Inc.. Ask for audit reports before you buy.
- https://www.runanywhere.ai/sample-app-privacy-policy
Reviews
No reviews yet
Reviews come from people who use MetalRT at work. Share how your team uses it to help other buyers decide.
Alternatives
SambaStack
by SambaNova
Full-stack enterprise AI platform combining purpose-built hardware and software to deploy, manage, and scale advanced AI models with high performance, security, and flexibility.
Developer Toolkit
by Fireworks AI
Build prototypes, evaluate fast, and scale with confidence.
Dedicated Inference
by Baseten
Run mission-critical inference at massive scale with the Baseten Inference Stack.
Dedicated, benchmarked inference endpoint with SLA-backed performance for your model on Crusoe's managed inference infrastructure.
FLUX [dev]
by Black Forest Labs
Self-hostable FLUX [dev] models available for download and hosting on customer infrastructure, with full control over deployment, fine-tuning, and customization.
Disaggregated Inference Engine
by Fireworks AI
The fastest and most efficient platform to serve open models.
Is this your product?
Claim it to keep details accurate and submit evidence for the next ranking review.
Claim MetalRT