MiniMax-M2.7
MiniMaxAIothertext

MiniMax-M2.7

Updated Jun 7, 2026
Parameters
228.7B
Context
204,800
License
other
Updated
Jun 7, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

49.6

AA Index

Coding

41.9

AA Index

Agentic

61.5

AA Index

Intelligence Index - MiniMax-M2.7 vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 4.8 (max)
61.4
closed
GPT-5.5 (xhigh)
60.2
closed
Claude Opus 4.7 (max)
57.3
closed
Gemini 3.1 Pro Preview
57.2
closed
Qwen3.7 Max
56.6
closed
Kimi K2.6
53.9
open
MiMo-V2.5-Pro
53.8
open
MiniMax-M2.7
49.6
open

Coding Index comparison

GPT-5.5 (xhigh)
59.1
closed
Claude Opus 4.8 (max)
56.7
closed
Gemini 3.1 Pro Preview
55.5
closed
Claude Opus 4.7 (Non-reasoning, high)
53.1
closed
GPT-5.3 Codex (xhigh)
53.1
closed
DeepSeek V4 Pro (Max)
47.5
open
Kimi K2.6
47.1
open
MiniMax-M2.7
41.9
open

Agentic Index comparison

Claude Opus 4.8 (max)
77.8
closed
GPT-5.5 (xhigh)
74.1
closed
Claude Opus 4.7 (max)
71.3
closed
Gemini 3.5 Flash (medium)
70.4
closed
MiniMax-M3
68.6
closed
MiMo-V2.5-Pro
67.4
open
DeepSeek V4 Pro (Max)
67.2
open
MiniMax-M2.7
61.5
open

Benchmark data from Artificial Analysis · updated 2026-06-07.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA87.4

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Too big for 24 GB at any quant
0 of 4 quantizations fit MiniMax-M2.7 with real runtime overhead.
Q8_0
245 GB
FP16
457 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve MiniMaxAI/MiniMax-M2.7

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

MiniMax-M2.7

MiniMax-M2.7 is a 228.7B-parameter other model from MiniMaxAI. It scores 49.6 on the Artificial Analysis Intelligence Index (coding 41.9). At Q4_K_M it needs roughly 133 GB of VRAM, placing it in the 48gb+ hardware tier.

Specifications

SpecValue
Parameters228.7B
Context length205K tokens
Licenseother
Modalitiestext
Released2026-04-09
WeightsMiniMaxAI/MiniMax-M2.7

Benchmarks

Artificial Analysis Intelligence Index - MiniMax-M2.7 vs. leading closed models:

ModelIntelligenceCodingGPQA
MiniMax-M2.749.641.987.4
GPT-5.5 (xhigh)60.259.193.5
Claude Opus 4.8 (max)61.456.792
Gemini 3.1 Pro Preview57.255.594.1
Grok 4.3 (high)53.24190.1

Source: Artificial Analysis (2026-06-04).

VRAM requirements

QuantVRAMRuns on
Q4_K_M~133 GBmulti-GPU / datacenter
Q5_K_M~162 GBmulti-GPU / datacenter
Q8_0~245 GBmulti-GPU / datacenter
FP16~457 GBmulti-GPU / datacenter

VRAM is estimated from parameter count; MoE models still need all weights resident.

How to run

vLLM:

vllm serve MiniMaxAI/MiniMax-M2.7

Popularity

MiniMax-M2.7 has 2,357,142 downloads in the last month on HuggingFace and 1,185 likes.

Frequently asked

Quick answers to common questions

How much VRAM does MiniMax-M2.7 need?

MiniMax-M2.7 with 228.7B parameters needs approximately 133 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is MiniMax-M2.7 better than other MiniMaxAI models?

MiniMax-M2.7 has 228.7B parameters with 204,800 context - a strong choice for general use.

What license is MiniMax-M2.7 under?

MiniMax-M2.7 is released under the other license, making it suitable for most commercial and personal projects.

What hardware runs MiniMax-M2.7 well?

With 228.7B parameters, MiniMax-M2.7 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for MiniMax-M2.7?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~162 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can MiniMax-M2.7's context window handle?

MiniMax-M2.7 supports a 204,800-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with MiniMax-M2.7?

MiniMax-M2.7 competes with other 114B–343B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.