MiMo V2.5 Pro — Hardware Requirements & GPU Compatibility
ChatFunctionsCode
MiMo V2.5 Pro is a 1023.2B-parameter open language model from Xiaomi. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 614.47 GB of VRAM — see which GPUs and Macs can run it below.
68.6K downloads
712 likesSpecifications
- Publisher
- Xiaomi
- Parameters
- 1023.2B
- Architecture
- MiMoV2ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 152,576
- Release Date
- 2026-04-27
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does MiMo V2.5 Pro Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 435.4 GB | 547.9 GB | 434.88 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 448.2 GB | 560.7 GB | 447.67 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 499.4 GB | 611.9 GB | 498.83 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 512.1 GB | 624.7 GB | 511.62 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 614.5 GB | 727.0 GB | 613.95 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 729.6 GB | 842.1 GB | 729.06 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 844.7 GB | 957.2 GB | 844.18 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 1023.8 GB | 1136.3 GB | 1023.24 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run MiMo V2.5 Pro?
Q4_K_M · 614.5 GBMiMo V2.5 Pro (Q4_K_M) requires 614.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 799+ GB is recommended. Using the full 1049K context window can add up to 112.5 GB, bringing total usage to 727.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run MiMo V2.5 Pro?
Q4_K_M · 614.5 GB2 devices with unified memory can run MiMo V2.5 Pro, including NVIDIA DGX H100.
Decent
— Enough memory, may be tightWhere to Download MiMo V2.5 Pro
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does MiMo V2.5 Pro need?
MiMo V2.5 Pro requires 614.5 GB of VRAM at Q4_K_M, or 2047.0 GB at BF16. Full 1049K context adds up to 112.5 GB (727.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1023.2B × 4.8 bits ÷ 8 = 613.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 113.1 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M614.5 GBQ4_K_M + full context727.0 GB- Can NVIDIA GeForce RTX 5090 run MiMo V2.5 Pro?
No — MiMo V2.5 Pro requires at least 281.9 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for MiMo V2.5 Pro?
For MiMo V2.5 Pro, Q4_K_M (614.5 GB) offers the best balance of quality and VRAM usage. Q5_K_S (704 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 281.9 GB.
VRAM requirement by quantization
IQ2_XXS281.9 GBQ2_K435.4 GBQ4_0512.1 GBQ4_K_M ★614.5 GBQ5_K_S704.0 GBBF162047.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MiMo V2.5 Pro on a Mac?
MiMo V2.5 Pro requires at least 281.9 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run MiMo V2.5 Pro locally?
Yes — MiMo V2.5 Pro can run locally on consumer hardware. At Q4_K_M quantization it needs 614.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of MiMo V2.5 Pro?
At Q4_K_M, the download is about 613.95 GB. The full-precision BF16 version is 2046.49 GB. The smallest option (IQ2_XXS) is 281.39 GB.
- Which GPUs can run MiMo V2.5 Pro?
No single consumer GPU has enough VRAM to run MiMo V2.5 Pro at Q4_K_M (614.5 GB). Multi-GPU or professional hardware is required.
- Which devices can run MiMo V2.5 Pro?
2 devices with unified memory can run MiMo V2.5 Pro at Q4_K_M (614.5 GB), including NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.