MiniMaxAI

MiniMax-M3

Name: MiniMax-M3
Author: MiniMaxAI

← All models

427B parameters · mixture-of-experts · Base · MiniMax family

minimax-community hash verified source matched revision pinned

Which version should I download?

Default pick: GGUF · UD-Q2_K_XL — Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation lane per DR-21). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick?

Format	Level	Size	Verdict	Est. speed	Quality note	Swarm	Download
GGUF	UD-Q2_K_XL	133.15 GB	Set your rig	—	Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation lane per DR-21). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice.	2S / 0L webseed OK	Magnet .torrent

GGUF · UD-Q2_K_XL

133.15 GB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation lane per DR-21). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice.

Magnet .torrent

Run it

Runtime completeness (UD-Q2_K_XL torrent): llama.cpp ✅ Ollama – vision sidecar –

– Ollama — runs the GGUF directly; no Modelfile bundled
– vision sidecar — not a vision model

Quant

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server

llama-server -m MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile)

FROM ./MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999

Create

ollama create minimaxai-minimax-m3 -f Modelfile

Run

ollama run minimaxai-minimax-m3

GGUF is not a first-class vLLM format.

vLLM GGUF support is experimental and single-file only; prefer safetensors/GPTQ/AWQ for production. If you must, pass the .gguf path to `vllm serve` with --load-format gguf on a recent vLLM.

Load MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

Not an MLX-format quant.

MLX runs MLX-format weights only (Apple Silicon). This quant is not an MLX build.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance: https://huggingface.co/MiniMaxAI/MiniMax-M3
Revision pin: 50942730318c7943fe83db7ec8e9f9177ecb1cf8
Manifest: Present

License

Name: minimax-community
Commercial use: unclear
Access: Open
Notes: MiniMax Community License (bundled verbatim). Grants free non-commercial rights to use/copy/modify/publish/DISTRIBUTE/sublicense -> redistribution permitted (preservation mirror). Commercial use by downstream products requires Built-with-MiniMax-M3 attribution + one-time notice (or written authorization above $20M yearly revenue) to [email protected]; prohibited-uses appendix applies. Verified 2026-07-12.

File hashes (SHA-256)

minimax-m3-ud-q2-k-xl/LICENSE b53f2fdda3049b0e9013207be51efc2d372cda1fcfdd8bb4bb8b22658ca5db9c
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf eed1a93ce4df7174594a3f681ae141562d2d6b708b989a4fe19de4cd75cd3268
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00002-of-00004.gguf d4a3e10d123a7c761fcaa7c5bcaf72e0861585aa7e2fe90a99f7e1ad4fc1957c
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00003-of-00004.gguf cc338e328a6cfea8b9e47476cbec5faeceb3bc6497cedc27df9985178d401c07
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00004-of-00004.gguf 152dafa2f842d36b74491038906e193af00d72098508f34aaba753b4998edb43
minimax-m3-ud-q2-k-xl/README.md ca005ef5e95860af62896c32d20decf9cd74c30ba8c5cf7f18f6fab1f496054a

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Reviews & presets

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

No community reports yet.

Recommended download