Instructions to use saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10

SGLang

How to use saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 with Docker Model Runner:
```
docker model run hf.co/saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10
```

saricles commited on Apr 17

Commit

32e1423

verified ·

1 Parent(s): a535890

Calibration notes: correct documentation — SWE-smith was silently dropped during REAP + NVFP4 calibration due to extractor bug

Browse files

Files changed (1) hide show

README.md +13 -0

README.md CHANGED Viewed

@@ -142,6 +142,19 @@ Per [MiniMax documentation](https://huggingface.co/MiniMaxAI/MiniMax-M2.7):
 Quantized for and tested on NVIDIA DGX Spark (GB10, 128 GB unified memory, 221 GB/s bandwidth). Should work on other Blackwell-class GPUs with NVFP4 tensor-core support. On Hopper-class hardware (H100/H200) the model will load and run, but the ignore list was tuned for Blackwell and will leave some performance on the table.
 ## Acknowledgments
 - Base model by [MiniMax](https://huggingface.co/MiniMaxAI)

 Quantized for and tested on NVIDIA DGX Spark (GB10, 128 GB unified memory, 221 GB/s bandwidth). Should work on other Blackwell-class GPUs with NVFP4 tensor-core support. On Hopper-class hardware (H100/H200) the model will load and run, but the ignore list was tuned for Blackwell and will leave some performance on the table.
+## Calibration notes (2026-04-17 correction)
+Both the upstream REAP pruning AND this NVFP4 calibration used the same dataset-extractor, which silently dropped texts from [`SWE-bench/SWE-smith-trajectories`](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories) because that dataset stores `messages` as a JSON-encoded string (not a list-of-dicts). Our extractor treated the string as an iterable of characters, found no dict entries, and collected zero texts.
+**Net effect on this artifact:**
+- REAP scoring used 5 of 6 documented datasets (see [base model card](https://huggingface.co/saricles/MiniMax-M2.7-REAP-172B-A10B-BF16) for details)
+- NVFP4 calibration used 5 of 6 documented datasets (same set: evol-codealpaca, xlam-function-calling, Mixture-of-Thoughts code/math/science)
+- SWE-smith-trajectories did NOT contribute to either pruning or quantization calibration
+**Fix:** the recipe script [`quantize-nvfp4-gb10-agentic.py`](./quantize-nvfp4-gb10-agentic.py) has been updated to `json.loads()` string-encoded `messages`, plus per-dataset assertions that fail the run if any dataset yields zero texts or if any selected dataset fails to load. Future variants will include SWE-smith as originally intended.
+**Practical implication:** agentic tool-use calibration still came through via xlam-function-calling (128 activations), and code/math/science reasoning via Mixture-of-Thoughts. What's missing is the specific long-horizon SWE-agent trajectory pattern. For typical OpenClaw / Aider / Claude Code use cases (single-call agentic + code), this is likely imperceptible; for long multi-step SWE-bench-style workflows, scales may be slightly misaligned at deep positions.
 ## Acknowledgments
 - Base model by [MiniMax](https://huggingface.co/MiniMaxAI)