Mellum2.1 12B (2.5B active) Thinking

on M4 16GB · MLX · 1,024 ctx

Oct 12, 2026

Throughput

64.0 t/s gen

Quant

NVFP4 (MLX)

System RAM

16 GB

Summary

User reports Mellum2.1 at 64 tokens/s at 1K context on an M4 16GB Mac. Setup is MLX with an NVFP4 conversion, 6.84 GB on disk. The user converted JetBrains' Mellum2.1 to MLX NVFP4 and asks for feedback on real tasks.

View source ↗