MiMo V2.5 Pro Base — Hardware Requirements & GPU Compatibility
ChatFunctionsCode
MiMo V2.5 Pro Base 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.
MiMo V2.5 Pro Base runs on a multi-GPU server
Q4_K_M needs ~616 GB · about 5× H200 SXM 141 GB · or Mac Studio (M3 Ultra, 512GB) at Q3_K_M (~20 tok/s)
Macs from 512 GB (Q3_K_M · ~20 tok/s)
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiMo V2.5 Pro Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve XiaomiMiMo/MiMo-V2.5-Pro-Base --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Rent 5× H200 SXM · Q4_K_M
- Estimated hourly price
- ~$17.95/hr
- est., whole server
- GPUs
- 5 GPUs
- 705 GB of VRAM
How Much VRAM Does MiMo V2.5 Pro Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 435.4 GB | 438.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on 7× H100 SXM 80 GB | |
| 499.4 GB | 502.7 GB | 3-bit medium — 3-bit medium quantization | Runs on 7× H100 SXM 80 GB | |
| 614.5 GB | 617.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 5× H200 SXM 141 GB | |
| 729.6 GB | 732.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 6× H200 SXM 141 GB | |
| 844.7 GB | 848 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 7× H200 SXM 141 GB | |
| 1023.8 GB | 1027.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 6× B200 192 GB | |
| 2047.0 GB | 2050.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 4 nodes of 8× H100 SXM |
Selected Q4_K_M
4-bit medium quantization616.0GBat 16K context
- Weights
- 614.0 GB
- KV cache
- 1.8 GB
- Overhead
- 0.3 GB
Server-class: ~616 GB at 16K context · about 5× H200 SXM 141 GB
Which Hardware Can Run MiMo V2.5 Pro Base?
Q4_K_M · 614.5 GBMiMo V2.5 Pro Base (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 consumer GPU has enough memory.
Needs server-class hardware
MiMo V2.5 Pro Base runs on a multi-GPU server · Q4_K_M needs ~616 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio (M3 Ultra, 512GB) | Q3_K_M | 500.9 GB | ~20 tok/s | 64K ctx | Mac Studio → | Q3_K_M · 500.9 GB · ~20 tok/s · 64K ctx |
| 8× H100 SXM 80 GB · 640 GB | Q3_K_M | 500.9 GB | — | 512K ctx | H100 SXM → | Q3_K_M · 500.9 GB · 512K ctx |
| 5× H200 SXM 141 GB · 705 GB | Q4_K_M | 616 GB | — | 128K ctx | H200 SXM → | Q4_K_M · 616 GB · 128K ctx |
| 4× B200 192 GB · 768 GB | Q4_K_M | 616 GB | — | 512K ctx | B200 → | Q4_K_M · 616 GB · 512K ctx |
Also: NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 436.9 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Kimi K2.6Moonshot AI | 120.9 | 617.6 GB | —needs > 24 GB | same size |
| InklingThinking Machines | 116.0 | 575.1 GB | —needs > 24 GB | same size |
| Ring 2.6 1TInclusion AI | — | 2052.6 GB | —needs > 24 GB | same size |
| MiMo V2.6 Pro MOPDXiaomi | — | 614.1 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Xiaomi
- Parameters
- 1023.2B
- Active parameters
- 43.9B per token
- Architecture
- MiMoV2ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 152,576
- Release Date
- 2026-04-27
- License
- MIT
Frequently Asked Questions
How much VRAM does MiMo V2.5 Pro Base need?
MiMo V2.5 Pro Base 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 113.1 GB (at full 1049K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run MiMo V2.5 Pro Base?
No — MiMo V2.5 Pro Base requires at least 435.4 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for MiMo V2.5 Pro Base?
For MiMo V2.5 Pro Base, Q4_K_M (614.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (729.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 435.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiMo V2.5 Pro Base on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run MiMo V2.5 Pro Base is Mac Studio (M3 Ultra, 512GB) at Q3_K_M; 1 of the 146 Macs we list can run it at some quantization. For Q4_K_M (614.5 GB) you need a Mac with more unified memory.
Can I run MiMo V2.5 Pro Base locally?
Yes — MiMo V2.5 Pro Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of MiMo V2.5 Pro Base?
At Q4_K_M, the download is about 613.95 GB. The full-precision BF16 version is 2046.49 GB. The smallest option (Q2_K) is 434.88 GB.
Which GPUs can run MiMo V2.5 Pro Base?
No single consumer GPU has enough VRAM to run MiMo V2.5 Pro Base at Q4_K_M (614.5 GB). Multi-GPU or professional hardware is required.
Which devices can run MiMo V2.5 Pro Base?
5 GB).