XI

Xiaomi MiMo VL Miloco 7B

XiaomiGGUF by xiaomi-open-sourceUpdated 2025-11-14
Download on Hugging Face
Parameters7.62B
Context125K
Layers36
Architectureqwen2vl
Smallest quant4.5 GB
Quick answer

Xiaomi MiMo VL Miloco 7B needs about 6.2 GB of memory at Q4_0 (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Xiaomi MiMo VL Miloco 7B – a multimodal 7.62B model for home scene understanding

The Xiaomi MiMo VL Miloco 7B is a 7.62‑billion parameter multimodal model built on the qwen2vl architecture. It supports vision and tool use and is optimized for resource‑constrained inference with a Q4_0 quantization.

Good at

  • Home scene recognition
  • Gesture interpretation
  • Instruction following

Limits

  • No vision support beyond the provided mmproj encoder
  • Limited to 128000 context tokens
  • License not specified

Best for

  • Smart home assistants
  • Home activity monitoring
  • Gesture‑based control

Who it’s for. Developers building home‑centric AI assistants or devices that need to interpret everyday activities and gestures. The model is suitable for applications requiring multimodal input with modest hardware resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.5 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use the Q4_0 quantized file (4.46 GB). It requires an estimated 6.2 GB of VRAM at 8 k context, which is within the 8 GB budget. No other quantizations are available in the file list.

What GPU do you need for Xiaomi MiMo VL Miloco 7B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_0 (4.5 GB file, about 6.2 GB in use).

Which Xiaomi MiMo VL Miloco 7B quant should you choose?

Q4_0 (4.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters7.62B
Layers36
Trained context128,000 tokens
KV cache (fp16)144 KB per token

Source

Quantized byxiaomi-open-source
FamilyXiaomi
Downloads (HF)661
Last updated2025-11-14

Frequently asked questions about Xiaomi MiMo VL Miloco 7B

How much VRAM does Xiaomi MiMo VL Miloco 7B need?

About 6.2 GB at Q4_0 with an 8K context window. That is the 4.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Xiaomi MiMo VL Miloco 7B on an 8 GB GPU?

Yes, with Q4_0: the 4.5 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Xiaomi MiMo VL Miloco 7B GGUF?

It depends on the quant: Q4_0 is 4.5 GB.

What context length does Xiaomi MiMo VL Miloco 7B support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Xiaomi MiMo VL Miloco 7B GGUF?

The files are on Hugging Face in the xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run MiMo VL Miloco 7B on 8 GB VRAM?

Yes, the Q4_0 quantized model (4.46 GB) needs about 6.2 GB of VRAM at 8 k context, fitting within an 8 GB GPU.

Does the model support vision tasks?

Yes, it includes a visual encoder (mmproj) in BF16 format for multimodal input.

What is the context length of the model?

The trained context token limit is 128000 tokens.

Similar models

Browse all →

More Xiaomi models

All Xiaomi →

Other small models

All small models →