Llama 3 8B Instruct Lite
Meta
🧠 Language Model
Fast lightweight Llama 3 for high-volume cost-sensitive use cases. 8K context.
Specifications
Context Window8,192 tokens
Max Output4,096 tokens
Speed●●●●● Very Fast
ModalitiesInput: text · Output: text
FeaturesTools: No Streaming: No
Pricing
Contact for pricing
Capabilities
More from Meta
Llama 4 Maverick
Most capable open-weight model. 400B params (17B active, 128-expert MoE). Multimodal with vision, tool use, and 524K context.
Llama 4 Scout
Fast multimodal model. 109B params (17B active, 16-expert MoE). Vision, tool use, 327K context. Fits on a single GPU.
Llama 3.3 70B
Proven workhorse model. 70B dense parameters, strong coding and instruction following. Text-only, 128K context.