Can an Open Model Do Security Research? Cantina’s apex-flash-1 Solves 40 of 60 Held-Out Bug Tasks
Cantina and Yeta Labs released apex-flash-1, an open model that solved 40 of 60 bug tasks.
Cantina Security and Yeta Labs released apex-flash-1, an open-weights model built for vulnerability research. It is a reinforcement-learning fine-tune of Z.ai’s GLM-5.3-Flash and is published on Hugging Face under the MIT license. The model solved 40 of 60 held-out bug-finding tasks. BF16 deployment needs about 640 GB of GPU memory and can run with vLLM, SGLang, or Transformers.
- apex-flash-1 is an RL fine-tune of GLM-5.3-Flash.
- MIT-licensed weights are available on Hugging Face.
- The model solved 40 of 60 held-out bug tasks.
- BF16 inference requires roughly 640 GB of GPU memory.
Cantina Security, with Yeta Labs, has released apex-flash-1, an open-weights model trained specifically for vulnerability research. It is a reinforcement learning fine-tune of Z.ai’s GLM-5.3-Flash, released on Hugging Face under the MIT license. Is it deployable? Yes, the MIT weights serve on vLLM, SGLang or Transformers, but BF16 needs roughly 640 GB of GPU memory. […] The post Can an Open Model Do Security Research? Cantina’s apex-flash-1 Solves 40 of 60 Held-Out Bug Tasks appeared first on MarkTechPost.
The full text could not be extracted from this site (paywall, bot protection or heavy scripting). Read it at marktechpost.com.