Instructions to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("thetom-ai/MiniMax-M2.7-ConfigI-MLX")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thetom-ai/MiniMax-M2.7-ConfigI-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "thetom-ai/MiniMax-M2.7-ConfigI-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "thetom-ai/MiniMax-M2.7-ConfigI-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "thetom-ai/MiniMax-M2.7-ConfigI-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "thetom-ai/MiniMax-M2.7-ConfigI-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thetom-ai/MiniMax-M2.7-ConfigI-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default thetom-ai/MiniMax-M2.7-ConfigI-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use thetom-ai/MiniMax-M2.7-ConfigI-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thetom-ai/MiniMax-M2.7-ConfigI-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "thetom-ai/MiniMax-M2.7-ConfigI-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Tom Turney commited on Apr 12

Commit

648505c

verified ·

1 Parent(s): 9b5afe9

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +146 -0

README.md ADDED Viewed

	@@ -0,0 +1,146 @@

+---
+base_model: MiniMaxAI/MiniMax-M2.7
+language:
+  - en
+license: other
+license_name: minimax-m2.7-non-commercial
+license_link: https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE
+pipeline_tag: text-generation
+tags:
+  - mlx
+  - turboquant
+  - turboquant-plus
+  - config-i
+  - moe
+  - apple-silicon
+quantized_by: pidtom
+inference: false
+---
+# MiniMax-M2.7 — TurboQuant+ Config-I (MLX)
+**93.5% MMLU at 87 GB. 61 tok/s decode. PPL 4.604.** 228B-parameter MoE compressed 62% with Config-I mixed-precision quantization. Standard MLX format — works with stock `mlx_lm` and `mlx-swift-lm`. No custom loaders required.
+Config-I quantization of [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) (228.7B total, ~1.4B active per token). The policy applies aggressive 2-bit compression to expert MLPs (where MoE is most tolerant), protects attention at 4-bit, and shields boundary layers and routing at full precision. See the [Config-I paper](https://github.com/TheTom/turboquant_plus/blob/main/docs/papers/weight-compression-tq4.md) for the policy derivation.
+## Compression
+| | Size |
+|---|---|
+| FP8 source | 230 GB |
+| **Config-I (3.25 bpw)** | **87 GB** |
+| **Reduction** | **62%** |
+## Quality
+**Perplexity:** 4.604 ± 0.042 (wikitext, 50 samples, 2048 seq length)
+**MMLU (200q, single-pass, reasoning ON):**
+| Subject | Score |
+|---|---|
+| Abstract Algebra | 18/20 |
+| Anatomy | 19/20 |
+| Astronomy | 19/20 |
+| College CS | 18/20 |
+| College Physics | 19/20 |
+| HS Biology | 20/20 |
+| HS Chemistry | 17/20 |
+| HS Math | 20/20 |
+| Logical Fallacies | 19/20 |
+| World Religions | 18/20 |
+| **TOTAL** | **187/200 (93.5%)** |
+Methodology: single-pass, 200 questions (10 MMLU subjects x 20), reasoning enabled, no retries, no few-shot, evaluated with `mlx_lm` on Apple M5 Max 128 GB.
+## Speed (Apple M5 Max 128 GB, mlx-swift-lm)
+Speed benchmarks measured with [ekryski/mlx-swift-lm](https://github.com/ekryski/mlx-swift-lm) (`consolidated` branch), which provides ~2.5x faster decode than Python `mlx_lm`.
+| Context | Prefill (t/s) | Decode (tok/s) |
+|---------|---------------|----------------|
+| 128 | 186 | 61.4 |
+| 256 | 268 | 60.4 |
+| 512 | 254 | 59.4 |
+| 1024 | 292 | 57.7 |
+| 2048 | 312 | 55.7 |
+| 4096 | 318 | 52.0 |
+| 8192 | 303 | 46.2 |
+| 16384 | 271 | 38.7 |
+## TurboQuant KV Cache Compression (mlx-swift-lm)
+KV cache compression via [ekryski/mlx-swift-lm](https://github.com/ekryski/mlx-swift-lm) (`consolidated` branch). Stacks on top of Config-I weight compression for additional memory savings at long context.
+| | bf16 | turbo4 | turbo2 |
+|---|---|---|---|
+| Per token | 248 KB | 62 KB | 31 KB |
+| Compression | 1x | 4x (75% saved) | 8x (88% saved) |
+| 8K context | 1.94 GB | 0.48 GB | 0.24 GB |
+| 16K context | 3.88 GB | 0.97 GB | 0.48 GB |
+| 32K context | 7.75 GB | 1.94 GB | 0.97 GB |
+| 64K context | 15.50 GB | 3.88 GB | 1.94 GB |
+| 128K context | 31.00 GB | 7.75 GB | 3.88 GB |
+**Max context on 128 GB M5 Max** (87 GB model, ~36 GB free):
+- bf16 KV: **149K tokens**
+- turbo4 KV: **595K tokens** (4x more context)
+- turbo2 KV: **1.2M tokens** (8x more context)
+PPL and NIAH results for KV compression coming soon.
+## Config-I Policy (MiniMax M2.7 Adaptation)
+| Component | Bits | Layers | Rationale |
+|-----------|------|--------|-----------|
+| Expert MLP gate/up | **2-bit** | middle 58 | 98%+ of params, MoE-tolerant |
+| Expert MLP down | **3-bit** | middle 58 | Write-back sensitivity (Config-I finding) |
+| Attention Q/K/V/O | **4-bit** | middle 58 | Uniform per layer |
+| Boundary (all tensors) | **8-bit** | first 2 + last 2 | Boundary layer protection |
+| MoE router | **f16** | all | Routing precision critical |
+| Embeddings + lm_head | **8-bit** | — | Protected |
+Uniform MLX quantization produces broken output (~25% MMLU, random guessing) on MiniMax at all bit levels because it compresses attention and routing to the same bits as expert MLPs. Config-I solves this by protecting the components that control coherence while compressing the 98% of parameters that tolerate it.
+## Compatibility
+| Field | Value |
+|-------|-------|
+| Format | MLX safetensors (standard) |
+| Avg bits | 3.249 bpw |
+| Runtime | `mlx_lm` (Python), `mlx-swift-lm` (Swift, 2.5x faster decode) |
+| Platform | Apple Silicon (recommended M-series Pro/Max/Ultra with 96GB+) |
+| Quantized on | 2026-04-12 |
+**No custom loader needed.** This is standard MLX per-layer quantization. Any tool that reads MLX safetensors with `config.json` quantization metadata will work.
+## How to Run
+```bash
+# Python (mlx_lm)
+pip install mlx-lm
+python -m mlx_lm.generate --model pidtom/MiniMax-M2.7-ConfigI-MLX --prompt "Hello"
+# Or load in code
+from mlx_lm import load, generate
+model, tokenizer = load("pidtom/MiniMax-M2.7-ConfigI-MLX")
+print(generate(model, tokenizer, prompt="Hello", max_tokens=256, temp=1.0, top_p=0.95))
+```
+> **Important:** MiniMax M2.7 is an always-reasoning model. Use `temp=1.0` — greedy/temp=0 causes infinite thinking loops.
+## What is Config-I?
+Config-I is a tensor-role-aware weight compression policy from TurboQuant+. Through systematic A/B isolation, it was discovered that attention tensors, FFN read projections (gate/up), FFN write-back projections (down), and boundary layers have dramatically different compression sensitivity. The key insight: **compression policy matters more than compression math** — which tensors to compress, which to protect, and how aggressively.
+Config-I achieves 27-38% size reduction at +1.0-3.9% PPL across Qwen and Phi model families (1.5B to 72B), validated by [independent third-party implementations](https://github.com/dhawalc/turboQuantDC).
+For MoE models like MiniMax M2.7, expert MLPs dominate parameter count but tolerate aggressive compression because only 8 of 256 experts are active per token. Config-I exploits this by compressing expert MLPs to 2-3 bit while protecting attention and routing at higher precision.
+- [Config-I Paper](https://github.com/TheTom/turboquant_plus/blob/main/docs/papers/weight-compression-tq4.md)
+- [Getting Started Guide](https://github.com/TheTom/turboquant_plus/blob/main/docs/getting-started.md)
+- [TurboQuant+ Repository](https://github.com/TheTom/turboquant_plus)
+---
+Quantized by [@pidtom](https://huggingface.co/pidtom) | [GitHub](https://github.com/TheTom) | [X](https://x.com/no_stp_on_snek) | [Sponsor](https://github.com/sponsors/TheTom)