Merve Noyan runs Qwen3.5-0.8B on Rabbit R1 via wllama after llama.cpp download fails

1. 2:16 PM
   merve@mervenoyannX

   Merve Noyan runs Qwen3.5-0.8B on a Rabbit R1 using wllama

   AIMerve Noyan says she could not download llama.cpp directly, so she built a version using wllama by @ngxson to run a 4-bit quantized Qwen3.5-0.8B on the Rabbit R1. The post is an update on her earlier plan to install llama.cpp on the device and build speech-to-speech apps.

   
2. 9:06 AM
   merve@mervenoyannX

   Merve Noyan considers running llama.cpp on her Rabbit R1

   AIHugging Face's Merve Noyan says she is considering installing llama.cpp on her Rabbit R1 and building speech-to-speech apps on it. She notes the device now lets owners vibe-code apps, run community creations on-device, or jailbreak it, and says she may need to upgrade its OS first. She states the device was sent to her for free and that the post is not a paid ad.

   

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.