MiniMax-M2.5: How to Run Guide

Run MiniMax-M2.5 locally on your own device!

MiniMax-M2.5 is a new open LLM achieving SOTA in coding, agentic tool use and search and office work, scoring 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp.

The 230B parameters (10B active) model has a 200K context window and unquantized bf16 requires 457GB. Unsloth Dynamic 3-bit GGUF reduces size to 101GB (-62%): MiniMax-M2.5 GGUF

All uploads use Unsloth Dynamic 2.0 for SOTA quantization performance - so 3-bit has important layers upcasted to 8 or 16-bit. You can also fine-tune the model via Unsloth, using multiGPUs.

⚙️ Usage Guide

The 3-bit dynamic quant UD-Q3_K_XL uses 101GB of disk space - this fits nicely on a 128GB unified memory Mac for ~20+ tokens/s, and also works faster with a 1x16GB GPU and 96GB of RAM for 25+ tokens/s. 2-bit quants or the biggest 2-bit will fit on a 96GB device.

For near full precision, use Q8_0 (8-bit) which utilizes 243GB and will fit on a 256GB RAM device / Mac for 10+ tokens/s.

Though not a must, for best performance, have your VRAM + RAM combined equal to the size of the quant you're downloading. If not, hard drive / SSD offloading will work with llama.cpp, just inference will be slower.

Recommended Settings

MiniMax recommends using the following parameters for best performance: temperature=1.0, top_p = 0.95, top_k = 40.

Default Settings (Most Tasks)
temperature = 1.0
top_p = 0.95
top_k = 40
repeat penalty = 1.0 or disabled

• Maximum context window: 196,608

• Min_P = 0.01 (default might be 0.05)

• Default system prompt:

You are a helpful assistant. Your name is MiniMax-M2.5 and is built by MiniMax.

Run MiniMax-M2.5 Tutorials:

For these tutorials, we will be utilizing the 3-bit UD-Q3_K_XL quant which fits in a 128GB RAM device.

✨ Run in llama.cpp

1

Obtain the latest llama.cpp on GitHub here. You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inference.

apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp

2

If you want to use llama.cpp directly to load models, you can do the below: (:Q3_K_XL) is the quantization type. You can also download via Hugging Face (point 3). This is similar to ollama run . Use export LLAMA_CACHE="folder" to force llama.cpp to save to a specific location. Remember the model has only a maximum of 200K context length.

Follow this for most default use-cases:

export LLAMA_CACHE="unsloth/MiniMax-M2.5-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/MiniMax-M2.5-GGUF:UD-Q3_K_XL \
    --ctx-size 16384 \
    --flash-attn on \
    --temp 1.0 \
    --top-p 0.95 \
    --min-p 0.01 \
    --top-k 40

3

Download the model via (after installing pip install huggingface_hub hf_transfer ). You can choose UD-Q3_K_XL (dynamic 4-bit quant) or other quantized versions like UD-Q6_K_XL . We recommend using our 4bit dynamic quant UD-Q3_K_XL to balance size and accuracy.

hf download unsloth/MiniMax-M2.5-GGUF \
    --local-dir unsloth/MiniMax-M2.5-GGUF \
    --include "*UD-Q3_K_XL*" # Use "*Q8_0*" for 8-bit

4

You can edit --threads 32 for the number of CPU threads, --ctx-size 16384 for context length, --n-gpu-layers 2 for GPU offloading on how many layers. Try adjusting it if your GPU goes out of memory. Also remove it if you have CPU only inference.

./llama.cpp/llama-cli \
    --model unsloth/MiniMax-M2.5-GGUF/UD-Q3_K_XL/MiniMax-M2.5-UD-Q3_K_XL-00001-of-00004.gguf \
    --temp 1.0 \
    --top-p 0.95 \
    --min-p 0.01 \
    --top-k 40 \
    --ctx-size 16384 \
    --seed 3407

🦙 Llama-server & OpenAI's completion library

To deploy MiniMax-M2.5 for production, we use llama-server or OpenAI API. In a new terminal say via tmux, deploy the model via:

./llama.cpp/llama-server \
    --model unsloth/MiniMax-M2.5-GGUF/UD-Q3_K_XL/MiniMax-M2.5-UD-Q3_K_XL-00001-of-00004.gguf \
    --alias "unsloth/MiniMax-M2.5" \
    --prio 3 \
    --temp 1.0 \
    --top-p 0.95 \
    --min-p 0.01 \
    --top-k 40 \
    --ctx-size 16384 \
    --port 8001

Then in a new terminal, after doing pip install openai, do:

from openai import OpenAI
import json
openai_client = OpenAI(
    base_url = "http://127.0.0.1:8001/v1",
    api_key = "sk-no-key-required",
)
completion = openai_client.chat.completions.create(
    model = "unsloth/MiniMax-M2.5",
    messages = [{"role": "user", "content": "Create a Snake game."},],
)
print(completion.choices[0].message.content)

📊 Benchmarks

You can view further below for benchmarks in table format:

Benchmark	MiniMax-M2.5	MiniMax-M2.1	Claude Opus 4.5	Claude Opus 4.6	Gemini 3 Pro	GPT-5.2 (thinking)
AIME25	86.3	83.0	91.0	95.6	96.0	98.0
GPQA-D	85.2	83.0	87.0	90.0	91.0	90.0
SciCode	44.4	41.0	50.0	52.0	56.0	52.0
IFBench	70.0	70.0	58.0	53.0	70.0	75.0
AA-LCR	69.5	62.0	74.0	71.0	71.0	73.0
SWE-Bench Verified	80.2	74.0	80.9	80.8	78.0	80.0
SWE-Bench Pro	55.4	49.7	56.9	55.4	54.1	55.6
Terminal Bench 2	51.7	47.9	53.4	55.1	54.0	54.0
HLE w/o tools	19.4	22.2	28.4	30.7	37.2	31.4
Multi-SWE-Bench	51.3	47.2	50.0	50.3	42.7	—
SWE-Bench Multilingual	74.1	71.9	77.5	77.8	65.0	72.0
VIBE-Pro (AVG)	54.2	42.4	55.2	55.6	36.9	—
BrowseComp (w/ctx)	76.3	62.0	67.8	84.0	59.2	65.8
Wide Search	70.3	63.2	76.2	79.4	57.0	—
RISE	50.2	34.0	50.5	62.5	36.8	50.0
BFCL multi-turn	76.8	37.4	68.0	63.3	61.0	—
τ² Telecom	97.8	87.0	98.2	99.3	98.0	98.7
MEWC	74.4	55.6	82.1	89.8	78.7	41.3
GDPval-MM	59.0	24.6	61.1	73.5	28.1	54.5
Finance Modeling	21.6	17.3	30.1	33.2	15.0	20.0

Coding Core Benchmark Scores

Search and Tool Use

Tasks Completed per 100

Office Capabilities