MiniMax (official)

Code: @MiniMaxAgent
MiniMax Design: @Hailuo_AI
API: Plan:

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash: Space Performance + Bunny Speed

🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.

💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.

API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.

Model weights will arrive on Oct 23.

API: https://t.co/fHRdSV73Hr
M Plan: https://t.co/XfJWSyauda
MiniMax Code for desktop: https://t.co/SGmLTI2HQm

[MiniMax (official) @MiniMax_AI]

Register here: https://t.co/6VOulzRJfE

[MiniMax (official) @MiniMax_AI]

M3.1 Flash is live on @FireworksAI_HQ . Let’s talk about how it was built—over cocktails.

Join MiniMax and @FireworksAI_HQ for Code & Cocktails in SF, where @Prof_OZ from Fireworks and @VictorSuOrtiz from MiniMax will discuss:
→ What went into building M3.1 Flash for long-running agents
→ How coding, tool use, and visual reasoning work together
→ What cheaper cached tokens mean for the cost of agent loops

Then drinks, bites, and time to compare notes with other builders.
📅 Tuesday, November 10 · Doors at 6 PM, fireside at 6:45 PM
📍 San Francisco · Venue shared after registration approval

Bring your questions. Registration below.
#MiniMax #FireworksAI #OpenModels #AgenticAI #AIEngineering

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash, on more of your hardware.

Quantizing a 428B model opens up more ways to run it locally. Lower-bit weights reduce the memory needed to load the model and the weight data moved during decoding. Making those savings useful takes careful calibration, efficient low-bit kernels, and hardware-aware placement of experts across GPU and system RAM.

Thank you to the builders doing that work:

• @UnslothAI @danielhanchen — 2-bit Dynamic GGUF weights at 143.9 GB, with calibration and fidelity testing across coding, tool use and other workloads.
• @ViC305 — SAGE-EXL3, token-level fidelity measurements and a single-DGX-Spark recipe.
• @PeasantSmith — Project Maya quants and expert offloading for local coding and tool use.
• @MiaAI_lab — EXL3-EAQ quantization work.
• @jundotkim + mlx-community — oQ quants and DSpark-powered decoding through oMLX on Apple Silicon.
• @AIatAMD — Quark MXFP4 adapted for AMD Instinct.
• @atomic_chat_hq — GGUFs for local desktop workflows.
• @superalesha — custom inference work combining quantized weights, expert caching and system RAM on 4× RTX 3090.
Every shared quant, kernel, measurement and recipe gives the next builder a better starting point. Thank you.

[SandBase @SandbaseAI]

⏳ 72 hours left for AI City Remix.

Miniature skylines. Pixel streets. Your city, your way.

Build with @MiniMax_AI M3.1 Flash on SandBase.

Free credits daily. A $3,000 grand prize in platform credits.

Put your city on our radar. 👇

[EvoMap @EvoMapAI]

MiniMax M3.1 Flash.
Now free on EvoX Agent.
Oct 28–30.

Experience what's possible. https://t.co/Bcph0CGuw3

[MiniMax (official) @MiniMax_AI]

💬 Live tomorrow with Fireworks AI: MiniMax M3.1 Flash.

Join @VictorSuOrtiz from MiniMax and @sophiamyang from @FireworksAI_HQ with your agent ideas, integration questions, or that one thing you’ve been meaning to ask.

Oct 28 · 10 AM PT

👉 RSVP: https://t.co/nIlwwcWB8j

[Fireworks @FireworksAI_HQ]

How good is MiniMax M3.1 Flash?

@VictorSuOrtiz (@MiniMax_AI) and Fireworks' @sophiamyang go live Oct 28 at 10 AM PT to break down what's new, what it's built for, and how to use it on Fireworks today.

Set a reminder:

https://t.co/yIGF3knIkX

[MiniMax (official) @MiniMax_AI]

Request an invitation → https://t.co/GLDKZjvHqG

[MiniMax (official) @MiniMax_AI]

MiniMax × @Pickford_AI bring Whispers to the Sydney Opera House during #NeurIPS2026.

Cinema that rewrites and reanimates itself in response to its audience.

December 7 · Private screening

[Pickford @Pickford_AI]

The show that re-writes and re-animates itself based on the audience is coming to the Sydney Opera House.

Pickford × MiniMax. December 7. During #NeurIPS2026.

https://t.co/Iklw6fP86r

@MiniMax_AI @Pickford_AI @ColeClifford @NeurIPSConf #InteractiveStorytelling #SydneyOperaHouse #minimax #Aifilmmaking

[MiniMax (official) @MiniMax_AI]

RSVP - https://t.co/GLDKZjvHqG

[EvoLink.ai @EvoLinkAi]

🚀MiniMax M3.1 Flash is now available on EvoLink
💻Great for software engineering, interactive creation and research
📺Check what @MiniMax_AI made to promote M3.1 Flash it self👇

[MiniMax (official) @MiniMax_AI]

@togethercompute Thanks @togethercompute for bringing LoRA-based post-training to MiniMax M3.1 Flash! 🐰

[Together AI @togethercompute]

minimax m3.1 flash is now available for post-training on together ai

run sft or rl with your own data, rewards + environments, while keeping the training loop in your own python code

take m3.1 flash and shape it for the agentic workload you need
https://t.co/0WHnc47hCY

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash meets the @UnslothAI community. 🐙🦥✨

Unsloth’s Dynamic GGUFs bring our 428B MoE model to a 143.9GB 2-bit footprint, with 91.5% top-1 token agreement in their evaluation across seven domains.

That means a lower memory barrier to self-hosting, deployment through Unsloth Desktop and llama.cpp, and an OpenAI-compatible API for existing apps and agents.

With 78K+ GitHub stars and over 500M model downloads on Hugging Face, Unsloth gives M3.1 Flash a path into an established community of developers running, evaluating and building with open models.

Open weights. Local control. More ways to build.

[Unsloth AI @UnslothAI]

MiniMax-M3.1-Flash can now run locally!

We made 2-bit GGUF retain 91.5% top 1 accuracy while being 45% smaller. Run on 150GB RAM.

MiniMax-M3.1-Flash is the strongest open model for its size & among the best overall.

GGUF: https://t.co/A8Xp9uqpq1
Guide: https://t.co/gW5gp25niu

[MiniMax (official) @MiniMax_AI]

Thank you 0G and the community for your support of M3.1 Flash! Hope to see more exciting projects from the community!

[0G Labs @0G_labs]

Heads up, M3.1 Flash gang .

Provider-side support for the free window changed, so free access ends early: Today, 16:00 UTC (not Oct 24).

But after that, it stays live on 0G Private Computer for 2 weeks at $0.09 in / $0.54 out per 1M tokens.

Thanks for the unhinged usage 🫡

[MiniMax (official) @MiniMax_AI]

More reference control. Fewer denoising steps. More places to run H3.

The latest community contributions span 8-step reference-conditioned video + audio, 4-step distillation, sparse attention, and reference-token compression - alongside serving and workflow integrations across GPU servers, TPUs, and Apple Silicon.

What matters is what this enables: more affordable experimentation, finer creative control, and more choices about where and how video generation runs. Open models become more useful when the community can improve the methods, adapt the runtime, and build workflows around them.

Credit to @haoailab @yisun0618 @lanfeng491270 @guocheng_qian @Alissonerdx @ddalcu @tazmannner @HaochengXiUCB @huggingface @Jhuaplin, and the PTD, DMAD, SparkH3, TorchTPU and FlashML teams - including Zhengming Yu and zechengtang on GitHub.

11 additions to the H3 ecosystem index. Thank you to everyone building, testing, and sharing.

https://t.co/F1S5IjUNi1

[MiniMax (official) @MiniMax_AI]

Open weights. Shared progress. MiniMax H3 is moving fast.

We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on.

Recent highlights:

• FastH3 — FastVideo, Nuva Lab and NVIDIA: 4-step distillation, now running on DGX Spark and Apple Silicon.

• Sol-H3 — NVIDIA’s SANA team: 15 seconds of 768p video + audio in 6.6 seconds on 8×B300, in the team’s warm-inference benchmark.*

• VDN — Haocheng Xi and the OpenVDN team: rethinking attention for faster H3 inference, with weights, training and inference code released.

• PDD — NVIDIA’s distillation method, brought to H3 by Alibaba PAI as 8-step Acc-LoRAs, now supported in ComfyUI.

• LightX2V — 4- and 8-step Turbo LoRAs, with workflows for text, image and reference-conditioned video + audio.

Behind every release are people training, optimizing, quantizing, testing and sharing. Special thanks to:
@haoailab @nuvalab @NVIDIAAI @xieenze_jr @HaochengXiUCB @ArashVahdat @julberner @LightX2V @ComfyUI
And to the individual contributors pushing the work forward:
@haozhangml @cxlcl1 @lawrence_cjs @yitongli165665 @haopengl33 @songhan_mit @shanasaimoe

Thank you for building with H3 and helping make it faster, more accessible, and more useful for the community. Powerful models go further when we build together. Keep pushing H3. Excited to see what comes next. 🚀

Explore the ecosystem: https://t.co/F1S5IjUNi1

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash is now on @tenstorrent Cloud -bringing frontier AI to Tensix silicon, Ethernet scale-out, and an open-source stack from the team led by Jim Keller.

Open weights. Diverse architectures. An open, heterogeneous AI future.🫡

[Tenstorrent @tenstorrent]

Today @MiniMax_AI released the open weights for MiniMax M3.1 Flash – available now on Tenstorrent Cloud.

Explore in the playground or connect to your agent harness. Start building → https://t.co/9IL1bl6E6S

[MiniMax (official) @MiniMax_AI]

@digitalocean Thanks for the day0 support!!

[MiniMax (official) @MiniMax_AI]

Thanks @FireworksAI_HQ for bringing M3.1 Flash to serverless on day 0! Looking sharp with the rebrand! 🎆

Try M3.1 Flash in serverless preview for your next multi-step agent workflow 🐰

[Fireworks @FireworksAI_HQ]

We have another release you don’t want to miss.

@MiniMax_AI M3.1 Flash is now live on Fireworks, day 0 with the open-weights release.

Built for agents that run long, multi-step work:

→ Cowork automation: 62.8 on AutomationBench-AA
→ Coding: 73.7% on DeepSWE v1.1
→ Visual reasoning: 91 on BabyVision
→ $0.15 input / $0.60 output / $0.015 cached per 1M tokens, half the price of M3

We've heard your feedback that you want more models on serverless. So we're launching more models in preview mode, starting today with M3.1 Flash, available for two weeks.

We'll be watching demand, and if the community likes it, we'll keep it around.

Try it now → https://t.co/RVwd3ETz9d