Snowflake / Arctic-LSTM-Speculator-Qwen3-32B-longcontext

Other380Updated Jun 30, 2026

Downloads

38

Likes

0

Last updated

Jun 30, 2026

License

apache-2.0

Build the fastest OSS vllm-based speculative decoding system for your own model, using ArcticTraining and ArcticInference!

Tags

  • pytorch
  • mlp_speculator

Technical specifications

ParametersNot available
LibraryNot available
LanguagesNot available
Base modelQwen/Qwen3-32B
Licenseapache-2.0