ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
MiniMax
Open-Weight MiniMax · MoE 427B / A23B · Text+Image+Video · BF16 / FP8

MiniMax-M3 (427B MoE) Architecture Parameters, Benchmarks & VRAM

MiniMax M3 427B/A23B multimodal sparse-attention MoE with 1M context and 524K max output.

🧬 MiniMax-M3 (427B MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (MiniMaxAI/MiniMax-M3) config.json & Model Card

HF Class: MiniMaxM3SparseForConditionalGeneration

1. Backbone & Dimensions

minimax_m3_vl
Total / Active Params
427B / 23B
Hidden Size (d_model)
6,144
FFN Intermediate Size
3,072
MoE Experts
128 Routed · Top-4 + 1 Shared
Activation / Norm
SiLU (SwiGLU) · ε=0.000001
Native Tensor Dtype
BF16 / FP8

2. Attention & Layer Layout

GQA
Num Hidden Layers
60 Layers
Hidden Layer Layout
60-Layer Sparse MoE (128 Experts, Top-4 Active)
Attention Heads (Q / KV)
64 Q / 4 KV (16:1 GQA)
Head Dimension
128
Vision Encoder / MTP
ViT 32L

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
1,048,576 tokens
RoPE Configuration
RoPE (原生 1,048,576 Context)
Vocab Size
200,064 (Untied)

📋 MiniMax-M3 (427B MoE) Official API & System Card Specifications

Verified against official MiniMax developer documentation & pricing

API Model ID: MiniMax-M3

1. Identity & Capabilities

API Spec
API Model ID
MiniMax-M3
Release Date
2026-06-01
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
部分支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
524,000 tokens
Input Modalities
Text + Image + Video
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 2.1
Cached Input / 1M
¥ 0.42 -80%
Output / 1M Tokens
¥ 8.5
Tiered Pricing Notes
MiniMax: Official MiniMax CN API endpoint

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Default Sampling
temperature=0.7 top_p=0.95 max_tokens=32,768

📊 MiniMax-M3 (427B MoE) Full Benchmark Scorecard

25 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 11 items

SWE-Bench Verified #9/59 80.5%

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

Claw-Eval #4/13 74.5%

Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.

MCP Atlas #20/39 74.2%

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

Terminal-Bench 2.1 #26/37 66%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

SWE-Bench Pro #20/52 59%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

PaperBench #3/3 52.6%

PaperBench is a benchmark for evaluating AI agents on their ability to replicate research papers. It tests models on complex, multi-step workflows involving code implementation, experimentation, and reproducing scientific results from academic publications.

NL2Repo #17/23 42.1%

NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.

SWE Atlas - Codebase QnA #5/5 37.9%

SWE Atlas - Codebase QnA evaluates a model's ability to answer questions about real codebases, measuring repository-level comprehension and the ability to reason about code structure, behavior, and intent across an entire project.

PostTrainBench #4/10 37.1%

PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as…

CL-bench #2/3 20.5%

CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.

FrontierCode 1.1 #22/23 14.7%

FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

🤖 Agents & Tools 8 items

SpreadSheetBench-v1 #1/3 89.4%

SpreadSheetBench-v1 evaluates office automation agents on spreadsheet reasoning and manipulation tasks, measuring the ability to analyze, transform, and operate on spreadsheet data through tools.

BrowseComp #20/54 83.5%

BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information.

BankerToolBench #3/4 76.1%

BankerToolBench is a public benchmark that evaluates models on banking and finance tool-use tasks. Models are scored against dataset rubrics, measuring their ability to correctly invoke tools and complete multi-step financial workflows.

DRACO #3/5 73.2%

DRACO is a deep research benchmark that evaluates an agent's ability to gather, synthesize, and reason over information to answer complex research questions. Scores are based on official rubrics per question, with the final score being the average across all questions.

OSWorld-Verified #18/26 70.1%

OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.

Finance Agent v2 #10/27 48.3%

Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

OfficeQA Pro #14/15 45.1%

OfficeQA Pro evaluates AI models on professional knowledge-work questions and tasks drawn from real office workflows, including document analysis, spreadsheet reasoning, and information synthesis across business domains.

APEX-Agents #12/15 27.7%

APEX-Agents is a benchmark evaluating AI agents on long horizon professional tasks that require sustained reasoning, planning, and execution across complex multi-step workflows.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

⚡ MiniMax-M3 (427B MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 427B / A23B·60L (d=6144)·64Q/4KV·Ctx 1000K·Text+Image+Video
Runnable Models →
512 GB Unified·1200 GB/s·Safe Usable 460.8 GB
Smooth Fit267.36 / 460.8 GB~53 tok/s
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
267.36/ 460.8 GB usable

Physical 512 GB · Load 58%

Theoretical Decode Speed
~53tokens/s

MoE: reads only 13.94 GB active weights/step

Max Context at Batch=1
1000K/ 1000K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 258.87 GBKV Cache (1×16K): 2.01 GBOverhead: 6.48 GB
Reserves ~10% unified memory for OS
🏃 Smooth & Snappy~9.4s for a 500-token response
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run minimax-m3-428b

Mac Studio M5 Ultra 512G Fits MiniMax-M3 (427B MoE) · Cost & TCO

Approx. $9,499 (~$19/GB VRAM) · 190W TDP

📊 MiniMax-M3 (427B MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 854 GB 2.01 GB 874.39 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 453.69 GB 2.01 GB 466.07 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 350.14 GB 2.01 GB 360.46 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 303.7 GB 2.01 GB 313.09 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 258.87 GB 2.01 GB 267.36 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 226.84 GB 2.01 GB 234.69 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 208.7 GB 2.01 GB 216.18 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 168.13 GB 2.01 GB 174.81 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for MiniMax-M3 (427B MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of MiniMax-M3 (427B MoE)?

MiniMax-M3 (427B MoE) uses MiniMaxM3SparseForConditionalGeneration with 60 layers (60-Layer Sparse MoE (128 Experts, Top-4 Active)), hidden_size=6144, 64 Q heads / 4 KV heads (head_dim=128), and vocab_size=200,064.

How much VRAM does MiniMax-M3 (427B MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), MiniMax-M3 (427B MoE) requires 267.36 GB VRAM. Full FP16 requires 874.39 GB.