deepseek-ai

	Model Configuration
Source Model	deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Inference API	MLC_LLM
Quantization	q4f16_ft
Model Type	qwen2
Vocab Size	152064
Context Window Size	131072
Prefill Chunk Size	8192
Temperature	0.6
Repetition Penalty	1.0
top_p	0.95
pad_token_id	0
bos_token_id	151646
eos_token_id	151643

See jetson-ai-lab.com/models.html for benchmarks, examples, and containers to deploy local serving and inference for these quantized models.