MiMo-V2.5-Pro
XiaomiMiMomittext

MiMo-V2.5-Pro

Updated Nov 12, 2026
Parameters
1023.2B
Context
1,048,576
License
mit
Q4 GGUF
629.61 GB
Updated
Nov 12, 2026

Q4 GGUF download: unsloth/MiMo-V2.5-Pro-GGUF - 629.61 GB on disk, read 2026-10-31. VRAM figures above are estimates; this is the actual file size.

Hosted API cost & speed

What it costs to rent this model instead of running it locally

MetricValue
Input (per 1M tokens)$0.39
Output (per 1M tokens)$0.78
Median speed (hosted API)52 tok/s

Median across hosted providers, measured by Artificial Analysis - updated 2026-11-12. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.

Arena rating (LMArena)

Human preference wins from head-to-head chat battles

MetricValue
Overall arena rating1464.1
Rank (overall)#38
Battle votes76,793

Overall rating published by LMArena on 2026-11-09 - a pairwise human-preference Elo across live chat battles; higher is better. Fetched 2026-11-12. Open-weights models compete head-to-head with proprietary ones here — no benchmark prompts, just what people pick.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA Diamond86.6
HLE35.7
SciCode50.6
IFBench79.9
Terminal-Bench43.2

Source: Artificial Analysis component evals - updated 2026-11-12.

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-Pro with real runtime overhead.
Q4_K_M
593 GB
Q5_K_M
726 GB
Q8_0
1095 GB
FP16
2046 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-Pro

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

Deep dive

Notes, sources, and the full write-up

MiMo-V2.5-ProLink to this section

MiMo-V2.5-Pro is a 1023.2B-parameter mit model from Xiaomi. At Q4_K_M it needs roughly 593 GB of VRAM, placing it in the 48gb+ hardware tier.

SpecificationsLink to this section

SpecValue
Parameters1023.2B
Context length1049K tokens
Licensemit
Modalitiestext
Released2026-04-27
WeightsXiaomiMiMo/MiMo-V2.5-Pro

VRAM requirementsLink to this section

QuantVRAMRuns on
Q4_K_M~593 GBmulti-GPU / datacenter
Q5_K_M~726 GBmulti-GPU / datacenter
Q8_0~1095 GBmulti-GPU / datacenter
FP16~2046 GBmulti-GPU / datacenter

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

How to runLink to this section

vLLM:

vllm serve XiaomiMiMo/MiMo-V2.5-Pro

PopularityLink to this section

MiMo-V2.5-Pro has 91,472 downloads in the last month on HuggingFace and 583 likes.

Frequently asked

Quick answers to common questions

How much VRAM does MiMo-V2.5-Pro need?

MiMo-V2.5-Pro with 1023.2B parameters needs approximately 593 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

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

MiMo-V2.5-Pro has 1023.2B parameters with 1,048,576 context - a strong choice for general use.

What license is MiMo-V2.5-Pro under?

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

What hardware runs MiMo-V2.5-Pro well?

With 1023.2B parameters, MiMo-V2.5-Pro 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-Pro?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~726 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

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

MiMo-V2.5-Pro 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-Pro?

MiMo-V2.5-Pro competes with other 512B–1535B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec