Kimi-K2.7-Code-NVFP4 is a specialized, quantized version of the Kimi model series optimized for code-related tasks. It uses the NVFP4 format for efficient inference while maintaining strong performance on programming, debugging, and software engineering benchmarks. The model is distributed on Hugging Face and can be used with standard transformer or vLLM inference stacks.
Kimi K2.7 Code is a Quantised & converted weights project. It focuses on running high-performance code generation models efficiently on consumer or edge hardware using specialized quantization. It is built as an open-source project for developers. Kimi K2.7 Code is open source under the Apache-2.0 license. It runs on the web, API, and the command line.
Decart AI builds and maintains Kimi K2.7 Code, and it first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 356 commits in the last 90 days. PulseGate's similarity index places it among 5 comparable projects. Key capabilities include Code Generation, Quantized Weights, and NVFP4 Format.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do