mimo-v2.6-flash-pro6000

All projects

Apps & Tools

mimo-v2.6-flash-pro6000

Run MiMo-V2.6-Flash-RL on a single RTX PRO 6000 at 41 tok/s.

bySSHdotCodes

Open source

mimo-v2.6-flash-pro6000 media is blocked

Allow external media to connect to the provider and play this content.

Description

An optimized runtime for running Xiaomi's 310B MiMo-V2.6-Flash-RL model on a single 96GB workstation GPU. It features a RAM expert cache system, NVFP4 weight support, and bit-exact output verification, achieving significant speedups and supporting up to 524K context.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.