This is converted Qwen3-14B model to Distributed Llama format. The model is quantized to Q40.
🚀 How to Run?
- ⏬ Download Distributed Llama repository.
- 🔨 Build Distributed Llama:
make dllama
- Download this model:
python launch.py qwen3_14b_q40
🚀 Run Distributed Llama:
./dllama chat --model dllama_model_qwen3_14b_q40 --tokenizer dllama_tokenizer_qwen3_14b.t --buffer-float-type q80 --nthreads 4 --max-seq-len 8192