LLM AtlasLLM AtlasSearch models

Provider analysis

Xiaomi

Publisher of the MiMo family of open-weight models including MiMo-V2-Flash (309B MoE), MiMo-Audio, MiMo-VL, and MiMo-Embodied.

Last verified: 2026-03-29Confidence: HighPrimary sources: 3

This provider page blends full-profile entries with broader verified listings. Use it to separate deeply evaluated flagship models from source-backed records that are tracked primarily for market visibility, access data, and freshness coverage.

Headquarters
Beijing, China
Founded
2010
Models tracked
3
Full-profile models
2
Catalog last verified
2026-03-29
Latest model verification
2026-03-29
Newest release tracked
2025-12-16
Confidence
High
Verified listings
1
Access mix
open-weight, self-hosted, hosted, api
API models
1

Tracked models available through provider-managed APIs.

Open-weight models
3

Models with downloadable weights or self-hosted distribution paths.

Primary source links
12

Total source references attached across this provider catalog.

Provider sources

Official links used to verify the provider profile and platform coverage.

Last verified: 2026-03-29

Xiaomi

MiMo-V2-Flash

MiMo

Xiaomi's MiMo-V2-Flash: 309B total/15B active MoE with hybrid sliding window attention, Multi-Token Prediction, and 256K context. Scores 94.1 on AIME 2025, 73.4 on SWE-Bench. Trained on 27T tokens with 6x KV-cache reduction.

Verified listing4 sources
textreasoningcodeopen-sourceopen-weightself-hostedhostedapi
Context
262,144
Input
Unpublished
Output
Unpublished
Coverage
Verified 2026-03-29

Xiaomi

MiMo-Audio-7B

MiMo

Xiaomi's MiMo-Audio 7B for any-to-any audio and text generation. Includes base and instruct variants.

Score 614 sources
textaudioopen-sourceopen-weightself-hosted
Context
131,072
Input
Not applicable
Output
Not applicable
Coverage
Full profile

Xiaomi

MiMo-VL-7B

MiMo

Xiaomi's MiMo-VL 7B vision-language model with 136K downloads on HuggingFace for image understanding and multimodal reasoning.

Score 664 sources
textvisionopen-sourceopen-weightself-hosted
Context
131,072
Input
Not applicable
Output
Not applicable
Coverage
Full profile