MiMo-Embodied-7B needs about 6.8 GB of memory at Q4_K_M (a 5.1 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-Embodied-7B: a 7.62B parameter vision‑language model for autonomous driving and embodied AI
MiMo-Embodied-7B is a 7.62B parameter model built on the qwen2vl architecture. It supports tools and was trained on 128000 context tokens. The model is released under the MIT license.
Good at
- Autonomous driving perception
- Embodied AI task planning
- Spatial understanding
Limits
- No vision support beyond tools
- Large memory requirement for high‑precision quant
- Requires 128000 context tokens
Best for
- Simulated driving environments
- Robotics task planning
- Spatial navigation tasks
Who it’s for. Developers building autonomous driving or embodied AI systems who need a vision‑language model with strong spatial reasoning. The model is suitable for research and prototyping where MIT licensing is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XS | 2.9 GB | 4.6 GB | Fits | Get file → | |
| IQ2_S | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 3.0 GB | 4.7 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_M | 3.2 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XXS | 3.6 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_M | 4.0 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 4.3 GB | 6.0 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_1 | 4.8 GB | 6.6 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 5.1 GB | 6.8 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.8 GB | 7.6 GB | Tight | Get file → | |
| Q5_1 | 6.1 GB | 7.8 GB | Tight | Get file → | |
| Q6_K_M | 6.6 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 8.1 GB | 9.8 GB | Too big | Get file → | |
| F16 | 11.5 GB | 13.2 GB | Too big | Get file → | |
| BF16 | 15.3 GB | 17.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (2.73 GB, 4.4 GB memory at 8k context) or Q4_K_M (5.11 GB, 6.8 GB memory). For 16 GB VRAM, Q5_K_M (5.85 GB, 7.6 GB memory) or Q8_0 (8.11 GB, 9.8 GB memory) provide higher precision. File sizes and memory estimates are approximate.
What GPU do you need for MiMo-Embodied-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: 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_NL (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.8 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 F16 (11.5 GB file, about 13.2 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-Embodied-7B quant should you choose?
Q4_K_M is the usual starting point for MiMo-Embodied-7B: it balances file size and quality well. Here it is a 5.1 GB file.
The Q8_0 file is 8.1 GB, about 1.6 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-Embodied-7B
How much VRAM does MiMo-Embodied-7B need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.1 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-Embodied-7B on an 8 GB GPU?
Yes, with Q5_1: the 6.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiMo-Embodied-7B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 2.7 GB, IQ2_XS is 2.9 GB, IQ2_S is 3.0 GB, Q2_K_S is 3.0 GB, IQ2_M is 3.1 GB and 19 more.
What context length does MiMo-Embodied-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 MiMo-Embodied-7B GGUF?
The files are on Hugging Face in the Mungert/MiMo-Embodied-7B-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-Embodied-7B 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-Embodied-7B on 8 GB VRAM?
Yes, using IQ2_XXS or Q4_K_M quantizations fits within 8 GB VRAM with approximate memory usage of 4.4 GB or 6.8 GB at 8k context.
Does the model support vision tasks?
The model supports tools but does not provide general vision‑language capabilities beyond the specified tools.