DeepSeek V4 Flash 284B (13B active)
on M5 Max 128GB · LM Studio · 1,048,576 ctx
Summary
User reports DeepSeek V4 Flash at ~26 tok/s generation and ~190 tok/s prompt processing on a MacBook Pro M5 Max with 128 GB unified memory.
Setup is LM Studio with antirez's deepseek_v4 llama.cpp fork sideloaded, IQ2XXS GGUF weights, F16 KV cache, and the full 1048576 token context. The model is a 256-expert MoE with ~80 GB resident.
The figures are approximate and the run is a workaround: upstream llama.cpp does not yet support the deepseek_v4 architecture and LM Studio's MLX runtime rejects V4 GGUFs. Long prompts beyond 16k tokens are flushed in 16k chunks due to the n_batch cap.