MiMo-V2.5
XiaomiMiMomittextvisionaudiovideo

MiMo-V2.5

Updated Jun 7, 2026
Parameters
310.8B
Context
1,048,576
License
mit
Updated
Jun 7, 2026

Intelligence benchmarks

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

Intelligence

49.0

AA Index

Coding

42.1

AA Index

Agentic

65.5

AA Index

Intelligence Index - MiMo-V2.5 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
MiMo-V2.5
49
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
MiMo-V2.5
42.1
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
MiMo-V2.5
65.5
open

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

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA84.9

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 MiMo-V2.5 with real runtime overhead.
Q5_K_M
221 GB
Q8_0
333 GB
FP16
622 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 XiaomiMiMo/MiMo-V2.5

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

Deep dive

Notes, sources, and the full write-up

MiMo-V2.5

MiMo-V2.5 is a 310.8B-parameter mit model from Xiaomi. It scores 49 on the Artificial Analysis Intelligence Index (coding 42.1). At Q4_K_M it needs roughly 180 GB of VRAM, placing it in the 48gb+ hardware tier.

Specifications

SpecValue
Parameters310.8B
Context length1049K tokens
Licensemit
Modalitiestext, vision, audio, video
Released2026-04-27
WeightsXiaomiMiMo/MiMo-V2.5

Benchmarks

Artificial Analysis Intelligence Index - MiMo-V2.5 vs. leading closed models:

ModelIntelligenceCodingGPQA
MiMo-V2.54942.184.9
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~180 GBmulti-GPU / datacenter
Q5_K_M~221 GBmulti-GPU / datacenter
Q8_0~333 GBmulti-GPU / datacenter
FP16~622 GBmulti-GPU / datacenter

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

How to run

vLLM:

vllm serve XiaomiMiMo/MiMo-V2.5

Popularity

MiMo-V2.5 has 210,786 downloads in the last month on HuggingFace and 282 likes.

Frequently asked

Quick answers to common questions

How much VRAM does MiMo-V2.5 need?

MiMo-V2.5 with 310.8B parameters needs approximately 180 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is MiMo-V2.5 better than other XiaomiMiMo models?

MiMo-V2.5 has 310.8B parameters with 1,048,576 context - a strong choice for general use.

What license is MiMo-V2.5 under?

MiMo-V2.5 is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs MiMo-V2.5 well?

With 310.8B parameters, MiMo-V2.5 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 MiMo-V2.5?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~221 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can MiMo-V2.5's context window handle?

MiMo-V2.5 supports a 1,048,576-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 MiMo-V2.5?

MiMo-V2.5 competes with other 155B–466B. 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.