LocalFit

MiMo-V2.6-Flash Superseded

XiaomiMiMo/MiMo-V2.6-Flash-RL

Released2026-09-22Size309B · 15B activeLicensemit

Files and memory at 8K context

QuantFileFiles+ KV + runtimeSmallest fitSource
MLX 4-bit mixed precision
nativ-community/MiMo-V2.6-Flash-RL-MLX-4bit
157 GiB36unknown256 GB Mac (cache unknown)HF files

No verified file: Q4_K_M, Q5_K_M, Q8_0, FP16, BF16, MLX 8-bit. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.

Quality

Artificial Analysis Intelligence Index

37.9

Variant: MiMo-V2.6-Flash · observed 2026-10-17 · source

Arena text rating

1,455

95% CI 1449–1462 · 10,917 votes · published 2026-10-15 · dataset

Exact listed model name; hosted reasoning/quantization may differ from local checkpoint.

Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.

Reported speeds 9

HardwareQuantBackendPrompt t/sGen t/sDateSource
Apple M3 Ultra (80-core GPU), 512 GB unified memory8bit (MiMo-V2.6-Flash-RL-oQ8e-mtp)MLX (oMLX server)57344.72026-10-14omlx.ai
Apple M3 Ultra (80-core GPU), 512 GB unified memory8bit (MiMo-V2.6-Flash-RL-oQ8e-mtp)MLX (oMLX server)64544.12026-10-14omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)47352.82026-10-07omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)42855.52026-10-07omlx.ai
Apple M5 Ultra (80-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-MOPD-oQ4e-mtp)MLX (oMLX server)1,87878.72026-10-07omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)40344.22026-10-07omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)48454.52026-10-07omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)33037.12026-10-07omlx.ai
Apple M3 Ultra (60-core GPU), 256 GB unified memory4bit (MiMo-V2.6-Flash-RL-MLX-4bit-MTP)MLX (oMLX server)45050.12026-10-07omlx.ai

Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database