aneforge/TinyLlama-1.1B-Chat-v1.0

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.1BQuant:BF16Context Size:2kPublished:Aug 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

aneforge/TinyLlama-1.1B-Chat-v1.0 is a 1.1 billion parameter chat-tuned causal language model, an unmodified duplicate of TinyLlama/TinyLlama-1.1B-Chat-v1.0. This model is specifically tagged for direct use with ANEForge, enabling efficient execution on Apple Neural Engine hardware without CoreML conversion. It provides a compact yet capable language model for on-device inference on Apple platforms.

Loading preview...

Overview

aneforge/TinyLlama-1.1B-Chat-v1.0 is a 1.1 billion parameter chat-tuned language model, directly sourced from TinyLlama/TinyLlama-1.1B-Chat-v1.0. Its primary distinction lies in its specific tagging and optimization for the ANEForge framework. This allows the model's weights to load and run natively on the Apple Neural Engine (ANE), bypassing the need for CoreML conversion and enabling efficient on-device inference.

Key Capabilities

  • Apple Neural Engine (ANE) Compatibility: Designed for direct execution on Apple Neural Engine hardware via ANEForge, optimizing performance for Apple devices.
  • Compact Size: With 1.1 billion parameters, it offers a lightweight solution for chat-based language tasks.
  • Chat Fine-tuning: Inherits the chat-tuned capabilities of the original TinyLlama model, suitable for conversational AI applications.

Good For

  • On-device AI Development: Ideal for developers building applications that require local, efficient LLM inference on Apple hardware.
  • Resource-Constrained Environments: Suitable for scenarios where a smaller model footprint and optimized hardware acceleration are crucial.
  • Experimentation with ANEForge: Provides a ready-to-use model for exploring the capabilities of the ANEForge framework for LLM deployment.

Finetunes
1 models