Llama
Open-weight language model family from Meta, released for local and self-hosted use.
Overview
Llama is a family of language models whose weights are published, so they can be run on your own hardware instead of only through an API. It solves the problem that most capable models are reachable only as a hosted service, which rules them out when data cannot leave your network or when per-token cost dominates. It exists because releasing weights turned out to build an ecosystem of fine-tunes and tooling around one architecture, and it is the model most local inference tools target first.
Technology Graph
How Llama connects to the rest of the stack.
Uses and depends on
- Transformer architecture Algorithms Llama based on Transformer High ✓ source
Applied to
- LoRA technique Techniques LoRA used for Llama High ✓ source
- Ollama tool Infrastructure Ollama used for Llama High ✓ source
- Quantization technique Techniques Quantization used for Llama High ✓ source
- TensorRT-LLM tool Infrastructure TensorRT-LLM used for Llama High ✓ source
- llama.cpp tool Infrastructure llama.cpp used for Llama High ✓ source
- vLLM tool Infrastructure vLLM used for Llama High ✓ source
Tools
Software that implements or integrates with Llama.
LLM Frameworks
Alternatives
Comparisons
Side-by-side breakdowns with the alternatives above.