Sakura MiMo V2.6 Flash MOPD P160 needs about 74.4 GB of memory at IQ2_XS (a 57.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 64.4 GB.
Sakura MiMo V2.6 Flash MOPD P160 – expert‑pruned, long‑context LLM
Sakura MiMo V2.6 Flash MOPD P160 is a 195 billion‑parameter MiMo model with 160 of 256 routed experts per layer. It is quantized to IQ2_XS and designed for long‑planning, coding and German instruction tasks. The model is released under the MIT license.
Good at
- Long‑horizon reasoning
- Tool‑call management
- German instruction handling
Limits
- Requires 74.4 GB VRAM at 8 k context
- No vision support
- MiMo‑specific SSD streaming setup needed
Best for
- Planning complex code projects
- Simulating long‑term game strategies
- Generating detailed German documentation
Who it’s for. Developers and researchers needing a large, locally runnable MiMo model with expert pruning for extended context. The model is community‑built and not an official Xiaomi release.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 57.8 GB | 74.4 GB | Too big | Get file → |
The only available quant is IQ2_XS, file size 57.76 GB. It requires approximately 74.4 GB VRAM at 8 k context. For lower VRAM budgets, no other quant is provided, so the model cannot be run with less memory than the estimate.
What GPU do you need for Sakura MiMo V2.6 Flash MOPD P160?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Sakura MiMo V2.6 Flash MOPD P160 quant should you choose?
IQ2_XS (57.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura MiMo V2.6 Flash MOPD P160
How much VRAM does Sakura MiMo V2.6 Flash MOPD P160 need?
About 74.4 GB at IQ2_XS with an 8K context window. That is the 57.8 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 Sakura MiMo V2.6 Flash MOPD P160 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 74.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Sakura MiMo V2.6 Flash MOPD P160 GGUF?
It depends on the quant: IQ2_XS is 57.8 GB.
What context length does Sakura MiMo V2.6 Flash MOPD P160 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 16.1 GB at 8K and 64.4 GB at 32K.
Where can I download Sakura MiMo V2.6 Flash MOPD P160 GGUF?
The files are on Hugging Face in the webmp3/Sakura-MiMo-V2.6-Flash-MOPD-P160-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura MiMo V2.6 Flash MOPD P160 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Sakura MiMo V2.6 Flash MOPD P160 on 8 GB VRAM?
No. The model requires about 74.4 GB VRAM at 8 k context, far exceeding 8 GB.
Does the model support vision or image inputs?
No. The model is text‑only and does not include vision capabilities.
Is the model officially released by Xiaomi?
No. It is an independent community build and not an official Xiaomi release.