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 7 quants, from 112.3 GB (Q2_K) to 186.8 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 64.4 GB.
MiMo V2 Flash Base is a 309B-parameter Mimo model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 7 quant files, from 112.3 GB (Q2_K) to 186.8 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 112.3 GB | 128.9 GB | Too big | Get file → | |
| Q3_K_S | 133.1 GB | 149.7 GB | Too big | Get file → | |
| Q3_K_M | 147.3 GB | 163.9 GB | Too big | Get file → | |
| Q3_K_L | 159.6 GB | 176.2 GB | Too big | Get file → | |
| IQ4_XS | 166.1 GB | 182.7 GB | Too big | Get file → | |
| Q4_K_S | 175.4 GB | 192.0 GB | Too big | Get file → | |
| Q4_K_M | 186.8 GB | 203.4 GB | Too big | Get file → |
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: 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 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 Q2_K at 112.3 GB, with the quality trade-offs that come with fewer bits. 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 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 128.9 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: Q2_K is 112.3 GB, Q3_K_S is 133.1 GB, Q3_K_M is 147.3 GB, Q3_K_L is 159.6 GB, IQ4_XS is 166.1 GB, Q4_K_S is 175.4 GB and 1 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-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.