MI

MiMo V2 Flash Base

MimoGGUF by mradermacherUpdated 2026-07-26
Download on Hugging Face
Parameters309B
Context256K
Layers48
Architecturemimo2
Smallest quant0.5 GB
Quick answer

MiMo V2 Flash Base needs about 203.4 GB of memory at Q4_K_M (a 186.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 21 quants, from 0.5 GB to 193.3 GB (Q4_1). Longer context needs more: at 32K tokens the KV cache alone adds about 64.4 GB.

MiMo V2 Flash Base – 309B parameter Mixture‑of‑Experts model

MiMo V2 Flash Base is a 309B parameter Mixture‑of‑Experts language model with a 262144 token context window. It supports tool usage and is released under the MIT license. The model is designed for high‑speed reasoning and agentic workflows.

Good at

  • High‑speed inference with MoE
  • Long‑context reasoning up to 256k tokens
  • Tool‑aware agentic tasks

Limits

  • Large VRAM requirement for higher‑quality quants
  • No vision support
  • Requires llama.cpp for GGUF usage

Best for

  • Agentic workflow automation
  • Complex reasoning with long context
  • Tool‑integrated LLM applications

Who it’s for. Developers building agentic or reasoning‑heavy applications who need a large‑parameter model with efficient inference. The model is suitable for users with access to high‑VRAM GPUs and familiarity with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 17.1 GB
Too big Get file →
IQ1_S62.5 GB 79.1 GB
Too big Get file →
IQ1_M69.4 GB 86.0 GB
Too big Get file →
IQ2_XXS80.9 GB 97.5 GB
Too big Get file →
IQ2_XS90.2 GB 106.8 GB
Too big Get file →
IQ2_S91.6 GB 108.2 GB
Too big Get file →
IQ2_M100.8 GB 117.4 GB
Too big Get file →
Q2_K_S104.4 GB 121.0 GB
Too big Get file →
Q2_K112.3 GB 128.9 GB
Too big Get file →
IQ3_XXS118.6 GB 135.2 GB
Too big Get file →
IQ3_XS125.8 GB 142.4 GB
Too big Get file →
Q3_K_S133.1 GB 149.7 GB
Too big Get file →
IQ3_S133.1 GB 149.7 GB
Too big Get file →
IQ3_M134.8 GB 151.4 GB
Too big Get file →
Q3_K_M147.3 GB 163.9 GB
Too big Get file →
Q3_K_L159.6 GB 176.2 GB
Too big Get file →
IQ4_XS164.4 GB 181.0 GB
Too big Get file →
Q4_0174.7 GB 191.3 GB
Too big Get file →
Q4_K_S175.4 GB 192.0 GB
Too big Get file →
Q4_K_M186.8 GB 203.4 GB
Too big Get file →
Q4_1193.3 GB 209.9 GB
Too big Get file →

For 8 GB VRAM use the 0.5 GB unknown quant (17.1 GB memory at 8k context). For 16 GB VRAM use the IQ1_S quant (62.5 GB file, 79.1 GB memory). For 24 GB VRAM use the IQ1_M quant (69.41 GB file, 86 GB memory). Memory estimates are approximate.

What GPU do you need for MiMo V2 Flash Base?

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: the best quant that fits is the main file (0.5 GB file, about 17.1 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 17.1 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 17.1 GB in use).

Which MiMo V2 Flash Base quant should you choose?

Q4_K_M is the usual starting point for MiMo V2 Flash Base: it balances file size and quality well. Here it is a 186.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemimo2
Parameters309B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)1920 KB per token

Source

Quantized bymradermacher
FamilyMimo
Licensemit
Downloads (HF)652
Last updated2026-07-26

Frequently asked questions about MiMo V2 Flash Base

How much VRAM does MiMo V2 Flash Base need?

About 203.4 GB at Q4_K_M with an 8K context window. That is the 186.8 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 MiMo V2 Flash Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiMo V2 Flash Base GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 62.5 GB, IQ1_M is 69.4 GB, IQ2_XXS is 80.9 GB, IQ2_XS is 90.2 GB, IQ2_S is 91.6 GB and 15 more.

What context length does MiMo V2 Flash Base support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 MiMo V2 Flash Base GGUF?

The files are on Hugging Face in the mradermacher/MiMo-V2-Flash-Base-i1-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 MiMo V2 Flash Base 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 MiMo V2 Flash Base on 8 GB VRAM?

Only the 0.5 GB unknown quant can be loaded, but it will require about 17.1 GB of VRAM at 8k context, so 8 GB is insufficient.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of MiMo-V2-Flash-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mimo models

All Mimo →

Other large models

All large models →