13:06
2026-09-24
dev.to
large-language-models
Running Qwen3.8-Flash-Next on a 128 GB Mac: The Expert-Pruning Trap, and a Memory-Mapped n-gram Table That Gets You to 240K Tokens
A developer got Qwen3.8-Flash-Next running on a 128 GB Mac Studio M4 Max by memory-mapping the model's 32 GB n-gram embedding table from disk on demand, avoiding both the quality loss of the expert-pr…