Qwen3.8 27B compressed ternary.
Params
27B
Fastest decode
54.7 tok/s
RTX 5060 Ti 16GB · PTQ1_0 · llama.cpp
Refusal
Official
Setups
2
Best reported pair · not live serving speed ↗
Runs on
Quoted one-stream decode on real boxes.
Get it running
- 1. DownloadPuts the weights on this computer.
huggingface-cli download prism-ml/Ternary-Bonsai-2-27B-gguf - 2. Start itUse this only if the download is GGUF.
llama-server -hf prism-ml/Ternary-Bonsai-2-27B-gguf - Open the weightsHugging Face ↗