MiniMax M3-VL — VRAM, Speed & Local Setup

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 26 czerwca 2026

Model library → MiniMax M3 → MiniMax M3-VL

PREVIEW — unverified. Vision-language variant of MiniMax M3, adding image (and reportedly video) understanding on top of the M3 backbone. Same ~230B/10B MoE footprint and 1M context. Treat all numbers as provisional pending the Hugging Face model card.

MiniMax M3-VL needs about 140 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters230 Billion (10B active)
Context window1,000,000
ArchitectureMixture-of-Experts (vision-language)
ProviderMiniMax
LicenceModified MIT (attribution required)
Specified atQ4_K_M
System RAM256 GB
Record updated2026-06-26

Licence

Modified MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K75.6 GB76.4 GB—Won't fit
Q3_K_M98.0 GB98.8 GB—Won't fit
Q4_K_M138.9 GB139.7 GB—Won't fit
Q5_K_M163.0 GB163.8 GB—Won't fit
Q6_K188.6 GB189.4 GB—Won't fit
Q8_0244.4 GB245.2 GB—Won't fit
F16460.0 GB460.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the MiniMax M3-VL VRAM calculator.

Buy This HardwareApple Mac Studio M2 Ultra — 192 GB VRAM · 60 W board powerDeploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs MiniMax M3-VL is the Apple M2 Ultra (192 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.
Apple Mac Studio M2 Ultra
192 GB VRAM · 60 W board power
Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.
Sprawdź cenę na Amazon

How to Run MiniMax M3-VL

Install Ollama, then run:

ollama run minimax-m3

Weights on Hugging Face: MiniMaxAI/MiniMax-M3-VL.

Best for: multimodal, vision, long context, enterprise.

Can I Run MiniMax M3-VL on My GPU?

Other MiniMax M3 Sizes

MiniMax M3-VL — Frequently Asked Questions

How much VRAM does MiniMax M3-VL need?
About 140 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does MiniMax M3-VL run on an RTX 4090 (24 GB)?
No. MiniMax M3-VL needs about 140 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run MiniMax M3-VL locally?
Install Ollama and run `ollama run minimax-m3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does MiniMax M3 come in?
MiniMax M3 230B-A10B (140 GB), MiniMax M3-VL (140 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All MiniMax M3 models | VRAM calculator | Check your own hardware