FitMyLLM
Xiaomi/Mixture of Experts

XMiMo V2.5 Pro

MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture.

chatcodingreasoningmultilingualmathvisionagentictool_use
1020B
Parameters (42B active)
1024K
Context length
9
Benchmarks
17
Quantizations
0
Architecture
MoE
Released
2026-04-22
Layers
48
KV Heads
4
Head Dim
192
Family
mimo

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.38303.9 GBlow
IQ2_M2.93374.1 GBlow
Q2_K3.16403.4 GBlow
IQ3_XXS3.25414.9 GBlow
IQ3_XS3.5446.7 GBlow
Q3_K_S3.64464.6 GBlow
IQ3_M3.76479.9 GBlow
Q3_K_M4510.5 GBlow
Q3_K_L4.3548.7 GBmoderate
IQ4_XS4.46569.1 GBmoderate
Q4_K_S4.67595.9 GBmoderate
Q4_K_M4.89624.0 GBgood
Q5_K_S5.57710.7 GBgood
Q5_K_M5.7727.2 GBgood
Q6_K6.56836.9 GBexcellent
Q8_08.51084.2 GBlossless
FP16162040.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN MIMO V2.5 PRO NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (9)

τ²-Bench94.2
GPQA Diamond86.6
IFBench79.9
AA Long Context73.3
AA Intelligence53.8
SciCode50.2
AA Coding45.5
Terminal-Bench43.2
HLE33.8

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run mimo:1020b-q4_K_M

Tag may need adjustment — check ollama.com/library/mimo for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceGGUF DownloadsBuild Hardware

Find the best GPU for MiMo V2.5 Pro

Build Hardware for MiMo V2.5 Pro
▸ SPEC SHEET

MiMo V2.5 Pro — 1020B MoE.

▸ SPECIFICATIONS
PARAMETERS
1020B (42B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
1024K tokens
CAPABILITIES
chat, coding, reasoning, multilingual, math, vision, agentic, tool_use
RELEASE DATE
2026-04-22
PROVIDER
Xiaomi
FAMILY
mimo
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.38303.9 GB65%
IQ2_M2.93374.1 GB75%
Q2_K3.16403.4 GB78%
IQ3_XXS3.25414.9 GB82%
IQ3_XS3.5446.7 GB84%
Q3_K_S3.64464.6 GB85%
IQ3_M3.76479.9 GB86%
Q3_K_M4510.5 GB88%
Q3_K_L4.3548.7 GB90%
IQ4_XS4.46569.1 GB92%
Q4_K_S4.67595.9 GB93%
Q4_K_M4.89624.0 GB94%
Q5_K_S5.57710.7 GB96%
Q5_K_M5.7727.2 GB96%
Q6_K6.56836.9 GB97%
Q8_08.51084.2 GB100%
FP16162040.5 GB100%
§ 01BENCHMARK SCORES
GPQA Diamond86.6
HLE33.8
AA Intelligence53.8
AA Coding45.5
aa_ifbench79.9
aa_terminal_bench43.2
aa_tau294.2
aa_scicode50.2
aa_lcr73.3