KernelLLM – Meta's new 8B SotA model(huggingface.co)
huggingface.co
KernelLLM – Meta's new 8B SotA model
https://huggingface.co/facebook/KernelLLM
1 comments
> On KernelBench-Triton Level 1, our 8B parameter model exceeds models such as GPT-4o and DeepSeek V3 in single-shot performance. With multiple inferences, KernelLLM's performance outperforms DeepSeek R1. This is all from a model with two orders of magnitude fewer parameters than its competitors.