MiniMax M2.5 — Hardware Requirements & GPU Compatibility
Chat
MiniMax M2.5 is a large-scale mixture-of-experts model from MiniMax, a well-funded Chinese AI company. With roughly 228 billion total parameters and a MoE architecture that activates only a fraction per token, it aims to deliver performance competitive with much larger dense models while keeping inference costs manageable. Running it locally requires substantial hardware due to its large parameter footprint, but quantized versions can make it accessible to users with multi-GPU setups looking for a powerful multilingual model with strong Chinese and English capabilities.
687.0K downloads
1.5K likesSpecifications
- Publisher
- MiniMaxAI
- Family
- MiniMax
- Parameters
- 228.7B
- Architecture
- MiniMaxM2ForCausalLM
- Context Length
- 196,608 tokens
- Vocabulary Size
- 200,064
- Release Date
- 2026-02-12
- License
- Other
Get Started
HuggingFace
How Much VRAM Does MiniMax M2.5 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 97.8 GB | 122.5 GB | 97.20 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 100.6 GB | 125.3 GB | 100.06 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 112.0 GB | 136.8 GB | 111.49 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 114.9 GB | 139.6 GB | 114.35 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 137.8 GB | 162.5 GB | 137.22 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 163.5 GB | 188.2 GB | 162.95 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 189.2 GB | 213.9 GB | 188.68 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 229.3 GB | 254.0 GB | 228.70 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run MiniMax M2.5?
Q4_K_M · 137.8 GBMiniMax M2.5 (Q4_K_M) requires 137.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 180+ GB is recommended. Using the full 197K context window can add up to 24.7 GB, bringing total usage to 162.5 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run MiniMax M2.5?
Q4_K_M · 137.8 GB6 devices with unified memory can run MiniMax M2.5, 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 MiniMax M2.5
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does MiniMax M2.5 need?
MiniMax M2.5 requires 137.8 GB of VRAM at Q4_K_M, or 458.0 GB at BF16. Full 197K context adds up to 24.7 GB (162.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 228.7B × 4.8 bits ÷ 8 = 137.2 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 25.3 GB (at full 197K context)
VRAM usage by quantization
Q4_K_M137.8 GBQ4_K_M + full context162.5 GB- Can NVIDIA GeForce RTX 5090 run MiniMax M2.5?
No — MiniMax M2.5 requires at least 63.5 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for MiniMax M2.5?
For MiniMax M2.5, Q4_K_M (137.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (157.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 63.5 GB.
VRAM requirement by quantization
IQ2_XXS63.5 GBQ3_K_S100.6 GBIQ4_XS123.5 GBQ4_K_M ★137.8 GBQ5_K_S157.8 GBBF16458.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MiniMax M2.5 on a Mac?
MiniMax M2.5 requires at least 63.5 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 MiniMax M2.5 locally?
Yes — MiniMax M2.5 can run locally on consumer hardware. At Q4_K_M quantization it needs 137.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MiniMax M2.5?
At Q4_K_M, MiniMax M2.5 can reach ~32 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 ÷ 137.8 × 0.65 = ~38 tok/s
Estimated speed at Q4_K_M (137.8 GB)
~38 tok/s~38 tok/s~32 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MiniMax M2.5?
At Q4_K_M, the download is about 137.22 GB. The full-precision BF16 version is 457.41 GB. The smallest option (IQ2_XXS) is 62.89 GB.
- Which GPUs can run MiniMax M2.5?
No single consumer GPU has enough VRAM to run MiniMax M2.5 at Q4_K_M (137.8 GB). Multi-GPU or professional hardware is required.
- Which devices can run MiniMax M2.5?
6 devices with unified memory can run MiniMax M2.5 at Q4_K_M (137.8 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.