Minimum VRAM
693GB
FP16 (full model) • Q4 option ≈ 174GB
Best Performance
AMD Instinct MI300X
~93 tok/s • Q4
Most Affordable
Apple M2 Ultra
Q4 • ~14 tok/s • From $5,999
Full-model (FP16) requirements are shown by default. Quantized builds like Q4 trade accuracy for lower VRAM usage.
Filter by quantization, price, and VRAM to compare performance estimates.
Showing Q4 compatibility. Switch tabs to explore other quantizations.
| GPU | Speed | VRAM Requirement | Typical price |
|---|---|---|---|
Apple M2 UltraEstimated Apple | ~14 tok/s Q4 | 174GB VRAM used192GB total on card | $5,999View GPU → |
Hardware requirements and model sizes at a glance.
| Component | Minimum | Recommended | Optimal |
|---|---|---|---|
| VRAM | 174GB (Q4) | 347GB (Q8) | 693GB (FP16) |
| RAM | 32GB | 64GB | 64GB |
| Disk | 50GB | 100GB | - |
| Model size | 174GB (Q4) | 347GB (Q8) | 693GB (FP16) |
| CPU | Modern CPU (Ryzen 5/Intel i5 or better) | Modern CPU (Ryzen 5/Intel i5 or better) | Modern CPU (Ryzen 5/Intel i5 or better) |
Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data
Common questions about running XiaomiMiMo/MiMo-V2-Flash locally
This model delivers strong local performance when paired with modern GPUs. Use the hardware guidance below to choose the right quantization tier for your build.
Use runtimes like llama.cpp, text-generation-webui, or vLLM. Download the quantized weights from Hugging Face, ensure you have enough VRAM for your target quantization, and launch with GPU acceleration (CUDA/ROCm/Metal).
Start with Q4 for wide GPU compatibility. Upgrade to Q8 if you have spare VRAM and want extra quality. FP16 delivers the highest fidelity but demands workstation or multi-GPU setups.
Q4_K_M and Q5_K_M are GGUF quantization formats that balance quality and VRAM usage. Q4_K_M uses ~174GB VRAM with good quality retention. Q5_K_M uses slightly more VRAM but preserves more model accuracy. Q8 (~347GB) offers near-FP16 quality. Standard Q4 is the most memory-efficient option for XiaomiMiMo/MiMo-V2-Flash.
Official weights are available via Hugging Face. Quantized builds (Q4, Q8) can be loaded into runtimes like llama.cpp, text-generation-webui, or vLLM. Always verify the publisher before downloading.
More model guides are on the way. Stay tuned.