MiMo-7B-Base
MiMo-7B-Base is an open-weights language model from Xiaomi, released June 5, 2025. It has 7.8B parameters (dense). The context window is 32K tokens.
We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential.
Check it against your own PC →
Can you run MiMo-7B-Base locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 6 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 4.2 GB | ~6 |
| 8 GB VRAM | Runs on GPU | IQ4_XS (good) | 7.2 GB | – | ~38 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.4 GB | – | ~33 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.4 GB | – | ~45 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.4 GB | – | ~80 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.4 GB | – | ~140 |
Benchmark results
Epoch AI has not published results for MiMo-7B-Base yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: XiaomiMiMo/MiMo-7B-Base
More from Xiaomi
MiMo V2.6 Flash MOPD · MiMo V2.6 Pro MOPD · MiMo-V2.6-Pro · MiMo-V2.6-Flash · MiMo V2.6 Pro RL · MiMo V2.6 Flash RL · MiMo-V2.5 · MiMo-V2.5-Pro