MiniMax-M2.1
MiniMax · moe · 229B parameters · 196,608 context
Parameters
229B
Context Window
192K tokens
Architecture
MoE
Best GPU
B200 SXM
Intelligence Brief
MiniMax-M2.1 is a 229B parameter Mixture-of-Experts (256 experts, 8 active) model from MiniMax, featuring Grouped Query Attention (GQA) with 62 layers and 3,072 hidden dimensions. With a 196,608 token context window, it supports tools, structured output, code, math, multilingual, reasoning. For self-hosted inference, B200 SXM delivers optimal throughput at $8522/month.
Recent changes
Loading…
Related models
5 suggestions- MiniMax-M2.5MiniMax-M2 · 7B$1.20/M out
- MiniMax-M2MiniMax-M2 · 7B$1.10/M out
mmE5-mllama-11b-instructintfloat · 10.6B—
multilingual-e5-large-instructintfloat · 0.6B—
Inflection 3Inflection · 100B$10.00/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
458.0 GB
FP8 Weights
229.0 GB
INT4 Weights
114.5 GB
Fits on (single GPU) — most practical first
Fits on (multi-GPU with Tensor Parallelism)
Multi-GPU configurations use Tensor Parallelism (TP) to split model layers across GPUs. Requires NVLink or NVSwitch interconnect for optimal performance.
GPU Compatibility Matrix
MiniMax-M2.1 is compatible with 8% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 2 GPUs · tensorrt-llm
100/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$8522
Cost/M Tokens
$11.58
FP8 · 2 GPUs · tensorrt-llm
100/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$8541
Cost/M Tokens
$11.61
FP8 · 2 GPUs · tensorrt-llm
100/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$12337
Cost/M Tokens
$16.77
Deployment Options
API Deployment
No API pricing available
Single GPU
B200 NVL (pair)
$9965/mo
Min VRAM: 229 GB
Multi-GPU
B200 SXM x2
280.0 tok/s
TP· $8522/mo
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, FP8)
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy MiniMax-M2.1
Self-Hosted Infrastructure
Similar Models
MiniMax-M2.5
229B params · moe
Quality: 50
from $1.20/M
MiniMax-M2
229B params · moe
Quality: 50
from $1.10/M
Qwen3-235B-A22B-Thinking-2507
235B params · moe
Quality: 50
from $0.60/M
Qwen 3 235B
235B params · moe
Quality: 83
from $0.00/M
DeepSeek Coder V2 236B
236B params · moe
Quality: 50
from $0.28/M
Frequently Asked Questions
How much VRAM does MiniMax-M2.1 need for inference?
MiniMax-M2.1 requires approximately 458.0 GB of VRAM at BF16 precision, 229.0 GB at FP8, or 114.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (253952 bytes per token) and activations (~0.00 GB).
What is the best GPU for MiniMax-M2.1?
The top recommended GPU for MiniMax-M2.1 is the B200 SXM (x2) using FP8 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $8522/month ($11.58/M tokens). Score: 100/100.
How much does MiniMax-M2.1 inference cost?
MiniMax-M2.1 inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.