MiMo VL 7B SFT 2508 needs about 6.4 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 15.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
MiMo VL 7B SFT 2508 – a vision‑language model with 7.62B parameters
MiMo VL 7B SFT 2508 is a qwen2vl architecture model with 7.62 billion parameters. It supports vision tasks and is released under the MIT license. The model was trained on a context of 128000 tokens.
Good at
- Vision‑language reasoning
- Image captioning
- Object detection in text queries
Limits
- No vision support beyond image input
- Requires 128000 token context for full training data
- MIT license limits commercial use without attribution
Best for
- Developers building VLM demos
- Researchers testing vision‑language benchmarks
- Educators creating interactive learning tools
Who it’s for. The model is suitable for developers and researchers who need a lightweight vision‑language model. It is ideal for those who can run it on local hardware with sufficient VRAM and RAM to handle the 128000 token context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q2_K | 3.1 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XS | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_M | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q2_K_L | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.8 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 6.0 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 6.2 GB | Fits | Get file → | |
| IQ4_NL | 4.5 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_XL | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_L | 5.1 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_L | 5.8 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 6.3 GB | 8.0 GB | Tight | Get file → | |
| Q6_K_L | 6.6 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 8.1 GB | 9.8 GB | Too big | Get file → | |
| BF16 | 15.3 GB | 17.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or IQ4_NL (file size 4.47 GB, memory 6.2 GB). For 12 GB VRAM, Q4_K_L (5.15 GB, 6.9 GB) or Q5_K_M (5.45 GB, 7.2 GB) are suitable. For 16 GB VRAM, Q6_K (6.26 GB, 8 GB) or Q6_K_L (6.56 GB, 8.3 GB) provide higher quality.
What GPU do you need for MiMo VL 7B SFT 2508?
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: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_XS (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.8 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.3 GB file, about 17.0 GB in use).
Which MiMo VL 7B SFT 2508 quant should you choose?
Q4_K_M is the usual starting point for MiMo VL 7B SFT 2508: it balances file size and quality well. Here it is a 4.7 GB file.
The Q8_0 file is 8.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 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
Source
Frequently asked questions about MiMo VL 7B SFT 2508
How much VRAM does MiMo VL 7B SFT 2508 need?
About 6.4 GB at Q4_K_M with an 8K context window. That is the 4.7 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 VL 7B SFT 2508 on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiMo VL 7B SFT 2508 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 2.9 GB, Q2_K is 3.1 GB, IQ3_XXS is 3.2 GB, IQ3_XS is 3.4 GB, Q3_K_S is 3.5 GB and 19 more.
What context length does MiMo VL 7B SFT 2508 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 MiMo VL 7B SFT 2508 GGUF?
The files are on Hugging Face in the bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-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 VL 7B SFT 2508 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 VL 7B SFT 2508 on 8 GB VRAM?
Yes, use the Q4_0 or IQ4_NL quantization which requires approximately 6.2 GB of VRAM at 8k context.
Does the model support video input?
No, the model only supports image input as a vision‑language model.
Is the model free to use for commercial projects?
The model is released under the MIT license, which allows commercial use with attribution.