MiMo V2.5 — Hardware Requirements & GPU Compatibility
ChatFunctions
MiMo V2.5 is a 310.8B-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 186.87 GB of VRAM — see which GPUs and Macs can run it below.
243.5K downloads
353 likesSpecifications
- Publisher
- Xiaomi
- Parameters
- 310.8B
- 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 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 132.5 GB | 183.9 GB | 132.08 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 136.4 GB | 187.8 GB | 135.96 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 151.9 GB | 203.3 GB | 151.50 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 155.8 GB | 207.2 GB | 155.39 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 186.9 GB | 238.3 GB | 186.47 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 221.8 GB | 273.3 GB | 221.43 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 256.8 GB | 308.2 GB | 256.39 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 311.2 GB | 362.6 GB | 310.78 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run MiMo V2.5?
Q4_K_M · 186.9 GBMiMo V2.5 (Q4_K_M) requires 186.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 243+ GB is recommended. Using the full 1049K context window can add up to 51.4 GB, bringing total usage to 238.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run MiMo V2.5?
Q4_K_M · 186.9 GB6 devices with unified memory can run MiMo V2.5, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 256GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download MiMo V2.5
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 need?
MiMo V2.5 requires 186.9 GB of VRAM at Q4_K_M, or 622.0 GB at BF16. Full 1049K context adds up to 51.4 GB (238.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 310.8B × 4.8 bits ÷ 8 = 186.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 51.8 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M186.9 GBQ4_K_M + full context238.3 GB- Can NVIDIA GeForce RTX 5090 run MiMo V2.5?
No — MiMo V2.5 requires at least 85.9 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?
For MiMo V2.5, Q4_K_M (186.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (190.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 85.9 GB.
VRAM requirement by quantization
IQ2_XXS85.9 GBIQ3_S132.5 GBQ3_K_L159.7 GBQ4_K_M ★186.9 GBQ4_K_L190.8 GBBF16622.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MiMo V2.5 on a Mac?
MiMo V2.5 requires at least 85.9 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 locally?
Yes — MiMo V2.5 can run locally on consumer hardware. At Q4_K_M quantization it needs 186.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MiMo V2.5?
At Q4_K_M, MiMo V2.5 can reach ~24 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 186.9 × 0.65 = ~28 tok/s
Estimated speed at Q4_K_M (186.9 GB)
~28 tok/s~28 tok/s~24 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MiMo V2.5?
At Q4_K_M, the download is about 186.47 GB. The full-precision BF16 version is 621.55 GB. The smallest option (IQ2_XXS) is 85.46 GB.
- Which GPUs can run MiMo V2.5?
No single consumer GPU has enough VRAM to run MiMo V2.5 at Q4_K_M (186.9 GB). Multi-GPU or professional hardware is required.
- Which devices can run MiMo V2.5?
6 devices with unified memory can run MiMo V2.5 at Q4_K_M (186.9 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.