Settings match the Recommended inference settings below. A second-pass retry of the 11 single-shot failures and decode-throughput measurement are pending; this card will be updated when those runs complete.

Recommended inference settings

These are the sampler parameters used for the HumanEval run above and are a good default for reasoning / code tasks:

python

sampler_params = {
    "temperature": 1.0,
    "top_p": 0.95,
    "top_k": 40,
    "repetition_penalty": 1.1,
    "max_tokens": 8192,
}

Chat template — thinking mode

MiniMax-M2.7 uses a <think>…</think> reasoning block. Important: the base chat template injects <think>\n at the end of the prompt before generation, so the model's output begins inside the reasoning block with no opening tag. To recover the final answer, strip everything up to and including the first </think>:

python

def strip_thinking(text: str) -> str:
    if "</think>" in text:
        return text.split("</think>", 1)[1].strip()
    return text.strip()

Give the model enough token budget that it can finish reasoning and emit the </think> closing tag — we recommend at least 4096, and 8192 for harder problems.

Usage

python

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors

model, tokenizer = load("baa-ai/MiniMax-M2.7-RAM-116GB-MLX")

sampler = make_sampler(temp=1.0, top_p=0.95, top_k=40)
logits_processors = make_logits_processors(repetition_penalty=1.1)

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Write a Python function that reverses a string."}],
    tokenize=False,
    add_generation_prompt=True,
)

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=8192,
    sampler=sampler,
    logits_processors=logits_processors,
)

if "</think>" in response:
    response = response.split("</think>", 1)[1].strip()
print(response)

Hardware

Apple Silicon Mac with ~128 GB unified memory recommended for comfortable inference.
Runs on less with swap, at substantially reduced throughput.

Variants

Variant	Size	Link
91 GB	96.4 GB	baa-ai/MiniMax-M2.7-RAM-91GB-MLX
100 GB	100.1 GB	baa-ai/MiniMax-M2.7-RAM-100GB-MLX
111 GB	110.9 GB	baa-ai/MiniMax-M2.7-RAM-111GB-MLX
116 GB	116.0 GB	baa-ai/MiniMax-M2.7-RAM-116GB-MLX
120 GB	120.1 GB	baa-ai/MiniMax-M2.7-RAM-120GB-MLX

Black Sheep AI Products

Shepherd — Private AI deployment platform that shrinks frontier models by 50-60% through RAM compression, enabling enterprises to run sophisticated AI on single GPU instances or Apple Silicon hardware. Deploy in your VPC with zero data leaving your infrastructure. Includes CI/CD pipeline integration, fleet deployment across Apple Silicon clusters, air-gapped and sovereign deployment support, and multi-format export (MLX, GGUF). Annual cloud costs from ~$2,700 — or run on a Mac Studio for electricity only.

Watchman — Capability audit and governance platform for compressed AI models. Know exactly what your quantized model can do before it goes live. Watchman predicts which capabilities survive compression in minutes — replacing weeks of benchmarking. Includes compliance-ready reporting for regulated industries, quality valley warnings for counterproductive memory allocations, instant regression diagnosis tracing issues to specific tensors, and 22 adversarial security probes scanning for injection, leakage, hallucination, and code vulnerabilities.

Learn more at baa.ai — Sovereign AI.

License

Inherited from the upstream MiniMax-M2.7 license: non-commercial use permitted; commercial use requires written authorization from MiniMax.

Quantized by baa.ai