428B
MiniMax
MiniMax M3
MiniMax's open-weight flagship, a Mixture-of-Experts model with roughly 428B total parameters and about 23B active per token. It is natively multimodal, accepting text, image, and video input, and supports a 1M-token context window. The model is built on MiniMax Sparse Attention (MSA), which the team reports gives more than 9x faster prefill and more than 15x faster decoding at 1M context versus M2. On agentic and coding benchmarks it scores 59.0% on SWE-Bench Pro, 66.0% on Terminal-Bench 2.1, 74.2% on MCP Atlas, 34.8% on SWE-fficiency, and 28.8% on KernelBench Hard.
428B paramsMoE1000K ctxMultimodal
View on Hugging FaceOur Take
A solid 428B-parameter MoE language model from MiniMax. Pulls ahead on graduate-level reasoning (GPQA) (93/100), so reach for it when that's the dimension that matters.
Run this onAMD Instinct MI325XCheapest card in our directory with comfortable headroom (256 GB) for this model at Q4 (~197.8 GB).
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Capabilities
Chat
Code Generation
Vision
Reasoning
Function Calling
Multilingual
Instruction Following
Model Specifications
Parameters428B
Active Params23B
ArchitectureMoE
Context Length1M tokens
ModalityMultimodal
ProviderMiniMax
Download Size1.7 TB
Community
Monthly Downloads167.7K
Likes1.5K
Last Updated2 months ago
Quick Start
Download from Hugging Face
Access model weights, configuration files, and documentation.
License
minimax-communityView Full License
Performance & Scoring
Benchmarks
MBA Open Score
55.4BB
Benchmark40%
61.8
Popularity25%
55.6
Efficiency20%
16.4
Versatility15%
90.0
Quantization Options
See how different quantization levels affect VRAM requirements and quality for this model.
| Format | VRAM Required | Quality | |
|---|---|---|---|
| Q2_K | 193.0 GB | Low | |
| Q4_K_MRecommended | 197.8 GB | Good | |
| Q5_K_M | 200.1 GB | Very Good | |
| Q6_K | 202.9 GB | Excellent | |
| Q8_0 | 208.7 GB | Near Perfect | |
| FP16 | 230.5 GB | Full |
Hardware That Runs This Model
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | Speed | VRAM |
|---|---|---|---|
| AMD Instinct MI355XAMD | SS | 32.6 tok/s | 197.8 GB |
| AMD Instinct MI325XAMD | AA | 24.4 tok/s | 197.8 GB |
| ASUS ExpertCenter Pro ET900N G3ASUS | AA | 28.9 tok/s | 197.8 GB |
| Dell Pro Max with GB300Dell | AA | 28.9 tok/s | 197.8 GB |
| HP ZGX Fury AI StationHP | AA | 28.9 tok/s | 197.8 GB |
Run Locally vs API
Energy cost on AMD Instinct MI300X (~22 tok/s, Q4_K_M) vs flagship API pricing.
| Source | Cost per 1M tokens |
|---|---|
Local (energy only)MiniMax M3 on AMD Instinct MI300X · ~22 tok/s · 750W | $1.16 |
GPT-5.6 LunaOpenAI · in $1.00 · out $6.00 | $2.50 |
Claude Fable 5Anthropic · in $10.00 · out $50.00 | $22.00 |
Gemini 3.5 FlashGoogle · in $1.50 · out $9.00 | $3.75 |
Grok 4.5xAI · in $2.00 · out $6.00 | $3.20 |
API prices blended at 70% input / 30% output.
Hardware amortisation not included. Run the full ROI calculator for payback math.
Rent in the Cloud
Cheapest current cloud rentals with at least 198 GB VRAM, refreshed hourly.
Advertising disclosure: we earn commissions when you shop through the links below.
| Option | Cost / GPU-hour |
|---|---|
AMD Instinct MI350XRunPod · Community · 288 GB VRAM | $0.50 |
AMD Instinct MI350XRunPod · Spot · 288 GB VRAM | $0.50 |
AMD Instinct MI350XDigitalOcean · Spot · 288 GB VRAM | $2.46 |
AMD Instinct MI355XDigitalOcean · Spot · 288 GB VRAM | $2.97 |
AMD Instinct MI325XDigitalOcean · On-Demand · 256 GB VRAM | $3.8 |
Per-GPU rate across RunPod, the Vast.ai marketplace, DigitalOcean, and Vultr.
Spot tier is interruptible. Plan for restarts when comparing against on-demand prices.
Related Models
Explore the Provider
See all MiniMax models
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every MiniMax model we track.
Explore the Family
See every MiniMax release
The full MiniMax family leaderboard with sizes, benchmark scores, and a release timeline.
Plan Your Setup
AI Hardware Calculator
Check which of your devices can run this model and how fast.
Live AI API Price Tracker
Compare hosted per-token prices before you commit to local hardware.
Self-Host vs Rent vs API
Break-even math for self-hosting, renting a GPU, or paying per token.
AI Stack Status Tracker
Live status for the hosted APIs you might use instead of running this locally.
