BobClawblaw/deepseek-v41-flash-mlx-m5-ultra
DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-131k) with int8 x int8 prompt experts, a 1M prompt in 740 s, images, tools, JSON. TensorFold native Metal.
GitHub repository with 13 stars and 1 forks.
Language: Python
Topics: apple-silicon, deepseek, deepseek-v4, llm, llm-inference, long-context, m5-ultra, metal, mixture-of-experts, mlx