LLMs
LLMs
Large language models (LLMs), APIs, agents, and harnesses.
- LLM models : giant tables of numbers
- LLM front ends : interacting with engines
- LLM engines : run LLM models
Tools
- llmspeed : Feel how fast a local LLM runs before you buy the hardware
- sparkDash : Multi-DGX Spark (or machines with NVIDIA GPUs) Monitoring Dashboard
Benchmarks
- LongTail-SWE : a benchmark of real GitHub issues in 13 underrepresented languages: Clojure, Dart, Elixir, Erlang, F#, Haskell, Julia, Kotlin, Lua, OCaml, R, Scala and Swift.
- QualityBench : QualityBench measures how good a model’s answers are, and how much quality a quantized build or a different engine loses, against any OpenAI-compatible endpoint.
- spark-bench : Mixed-capability LLM benchmark for DGX Spark.
- tool-eval-bench : A tool-calling quality benchmark for LLMs in agentic workflow.
Last updated on