ModelLLMsv1.1B

TinyLlama 1.1B

by Zhang Peiyuan et al. (Academic) · open-source · Last verified 2026-03-17

TinyLlama is a compact 1.1 billion parameter language model trained on approximately 3 trillion tokens using the LLaMA architecture and tokenizer. It achieves impressive performance for its size, particularly on commonsense reasoning tasks, making it ideal for resource-constrained environments and real-time applications.

https://github.com/jzhang38/TinyLlama ↗

C+

C+—Average

Adoption: BQuality: BFreshness: BCitations: BEngagement: F

Specifications

License: Apache 2.0
Pricing: open-source
Capabilities: text-generation, instruction-following, on-device-inference, low-latency-serving
Integrations: Hugging Face, Ollama, llama.cpp, MLC LLM
Use Cases: embedded AI applications, real-time chatbots, IoT edge inference, developer prototyping
API Available: Yes
Parameters: ~1.1B
Context Window: 2K
Modalities: text
Training Cutoff: 2023
Tags: small, edge, llama, open-source, efficient
Added: 2026-03-17
Completeness: 100%

Index Score

55.2

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service