Kimi-K3.1-Dflash2-Preview
RadixArk · Kit
Speeds up Kimi-K3.1-Pro serving by drafting blocks of tokens that the main model checks in one pass. A draft model for SGLang users, used alongside the target…
New
RadixArk · Kit
Speeds up Kimi-K3.1-Pro serving by drafting blocks of tokens that the main model checks in one pass. A draft model for SGLang users, used alongside the target…
Grawnch · Kit
Runs a heavily compressed copy of the 2.8T-parameter Kimi-K3.1-Pro, tuned for coding and math. Made by Grawnch with a three-tier mixed-bit scheme, for people w…
fulcrumresearch · Kit
Writes in the style of a named author as a LoRA adapter for Kimi-K3, in PEFT format. For writers and developers who already run the Kimi K3 base model.
openinterpreter · Kit
The new Rust version of Open Interpreter, a coding agent for your terminal, built on OpenAI’s Codex. You bring the model, from ChatGPT or an API key to Kimi K3…