This is converted Qwen3.5-9B model to Distributed Llama format. The model is quantized to Q40.
🚀 How to Run?
- ⏬ Download this repository.
- ⏬ Download Distributed Llama repository.
- 🔨 Build Distributed Llama:
make dllama
🚀 Run Distributed Llama:
./dllama chat --model models/qwen3_5_9b_q40/dllama_model_qwen3_5_9b_q40.m --tokenizer models/qwen3_5_9b_q40/dllama_tokenizer_qwen3_5_9b_q40.t --buffer-float-type q80 --nthreads 8 --max-seq-len 4096 --chat-template chatml_thinking