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 428B / A23B · Text+Image+Video · FP8 QAT

MiniMax-M3.1-Flash (428B MoE) Architecture Parameters, Benchmarks & VRAM

428B total / 23B active native multimodal 1M-context MoE with MiniMax Sparse Attention & DSpark draft head.

🧬 MiniMax-M3.1-Flash (428B MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (MiniMaxAI/MiniMax-M3.1-Flash) config.json & Model Card

HF Class: MiniMaxM3SparseForConditionalGeneration

1. Backbone & Dimensions

minimax_m3_vl
Total / Active Params
428B / 23B
Hidden Size (d_model)
6,144
FFN Intermediate Size
3,072
Activation / Norm
SiLU (SwiGLU) · ε=1e-6
Native Tensor Dtype
FP8 QAT

2. Attention & Layer Layout

HYBRID
Num Hidden Layers
60 Layers
Hidden Layer Layout
60-Layer MiniMax Sparse Attention (MSA) + 128-Expert MoE (Top-4 + 1 Shared)
Attention Heads (Q / KV)
64 Q / 4 KV (16:1 GQA)
Head Dimension
128
Linear / KV Compression
End-to-end MiniMax Sparse Attention (MSA) + DSpark speculative head · 32L ViT
Vision Encoder / MTP
ViT 32L

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
1,048,576 tokens
RoPE Configuration
MSA Long-Context RoPE (原生 1,048,576 / 1M Context)
Vocab Size
200,064 (Untied)
Special Token IDs
BOS: 200019 · EOS: 200020

📋 MiniMax-M3.1-Flash (428B MoE) Official API & System Card Specifications

Verified against official MiniMax developer documentation & pricing

API Model ID: MiniMax-M3.1-Flash

1. Identity & Capabilities

API Spec
API Model ID
MiniMax-M3.1-Flash
Release Date
2026-10-19
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
1,024,000 tokens (1024K)
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
¥ 1
Cached Input / 1M
¥ 0.1 -90%
Output / 1M Tokens
¥ 4
Tiered Pricing Notes
MiniMax: Official MiniMax CN API endpoint

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1466 AA Index 46
💻 Coding
DeepSWE v1.1 73.7 %
🤖 Agentic
CyberGym 82.2 %

CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.

🤖 Agentic
BankerToolBench 76.2 %

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.

🤖 Agentic
OSWorld 2.0 61.7 %

OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.

👁️ Multimodal
BabyVision (w/ Tools) 91 %
👁️ Multimodal
CharXiv RQ 82.5 %

Scientific chart synthesis and quantitative reasoning

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Default Multimodal & Agent Mode
temperature=1 top_p=0.95 max_tokens=65,536

📊 MiniMax-M3.1-Flash (428B MoE) Full Benchmark Scorecard

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

⚔️ Compare head-to-head

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

⚡ MiniMax-M3.1-Flash (428B MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 428B / A23B·60L (d=6144)·64Q/4KV·Ctx 1M·Text+Image+Video
Runnable Models →
512 GB Unified·1200 GB/s·Safe Usable 460.8 GB
Smooth Fit267.98 / 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
267.98/ 460.8 GB usable

Physical 512 GB · Load 58.2%

Theoretical Decode Speed
~53tokens/s

MoE: reads only 13.94 GB active weights/step

Max Context at Batch=1
1M/ 1M

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 259.47 GBKV Cache (1×16K): 2.01 GBOverhead: 6.49 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-m3.1:flash

Mac Studio M5 Ultra 512G Fits MiniMax-M3.1-Flash (428B MoE) · Cost & TCO

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

📊 MiniMax-M3.1-Flash (428B MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 856 GB 2.01 GB 876.43 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 454.75 GB 2.01 GB 467.16 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 350.96 GB 2.01 GB 361.29 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 304.42 GB 2.01 GB 313.82 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 259.47 GB 2.01 GB 267.98 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 227.38 GB 2.01 GB 235.24 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 209.19 GB 2.01 GB 216.68 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 168.53 GB 2.01 GB 175.21 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for MiniMax-M3.1-Flash (428B MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of MiniMax-M3.1-Flash (428B MoE)?

MiniMax-M3.1-Flash (428B MoE) uses MiniMaxM3SparseForConditionalGeneration with 60 layers (60-Layer MiniMax Sparse Attention (MSA) + 128-Expert MoE (Top-4 + 1 Shared)), hidden_size=6144, 64 Q heads / 4 KV heads (head_dim=128), and vocab_size=200,064.

How much VRAM does MiniMax-M3.1-Flash (428B MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), MiniMax-M3.1-Flash (428B MoE) requires 267.98 GB VRAM. Full FP16 requires 876.43 GB.