MiniMax-M3 MLX - a pipenetwork Collection

pipenetwork 's Collections

Kimi-K3.1-Pro REAP80 code (MLX, 512 GB Mac)

Ternary-Bonsai-2 MLX

DeepSeek-V4.1-Flash MLX

GLM-5.3-Flash MLX

Qwen3.8-Flash-Next MLX

Qwen3.8-2.4T-A95B MLX (REAP)

Muse-Glimmer 30B MLX

Inkling-Small · MLX

DeepSeek-V4-Flash · MLX

Nemotron TwoTower · MLX

Qwen3.6-35B-A3B — MLX

Ornith-1.0-397B — MLX

GLM-5.2 REAP (expert-pruned)

Rio-3.1-Open-30B MLX

Gemma-4-26B-A4B-it MLX

Gemma-4-31B-it MLX

Kimi-K2.7-Code MLX

Holo-3.1 MLX (computer-use)

Frog (SWE/debugging) MLX

Nemotron-3 MLX (Apple Silicon)

MiniMax-M3 MLX

updated Jun 13

MLX (Apple Silicon) text-only conversions of MiniMax-M3 (427B MoE): 3-bit to 8-bit plus a mixed-precision build.

pipenetwork/MiniMax-M3-MLX-8bit

Text Generation • 426B • Updated Jun 13 • 56 • 1

Note 8-bit · ~453GB · near-lossless
pipenetwork/MiniMax-M3-MLX-6bit

Text Generation • 426B • Updated Jun 13 • 38 • 1

Note 6-bit · ~346GB · high quality
pipenetwork/MiniMax-M3-MLX-4bit

Text Generation • 426B • Updated Jun 13 • 133 • 1

Note 4-bit · ~240GB · balanced default
pipenetwork/MiniMax-M3-MLX-mixed-3_6bit

Text Generation • 426B • Updated Jun 13 • 120 • 2

Note mixed · ~191GB · experts@3-bit, attn/embeds/router@6-8-bit · best quality-per-GB
pipenetwork/MiniMax-M3-MLX-3bit

Text Generation • 426B • Updated Jun 13 • 117

Note 3-bit · ~186GB · smallest