This repository mirrors the Qwen3.5-0.8B-Q4_K_M.gguf quantization from unsloth/Qwen3.5-0.8B-GGUF for Notavox on-device, text-only voice-note summarization.

Included file

File	Size	SHA-256
`Qwen3.5-0.8B-Q4_K_M.gguf`	532,517,120 bytes	`bd258782e35f7f458f8aced1adc053e6e92e89bc735ba3be89d38a06121dc517`

Source revision: 6ab461498e2023f6e3c1baea90a8f0fe38ab64d0.

The visual projector is intentionally not included because Notavox uses this model for text-only transcript summarization. Recommended mobile runtime settings: 8,192-token context, non-thinking mode, and chunked summarization for long transcripts.

newbeeforever/qwen3.5-0.8b-gguf

Notavox Qwen3.5 0.8B GGUF

Included file

newbeeforever/
qwen3.5-0.8b-gguf