Instructions to use Outlier-Ai/Outlier-Quick-26B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Outlier-Ai/Outlier-Quick-26B-MLX-4bit 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("Outlier-Ai/Outlier-Quick-26B-MLX-4bit")

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 Outlier-Ai/Outlier-Quick-26B-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"

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": "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Outlier-Ai/Outlier-Quick-26B-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Outlier-Ai/Outlier-Quick-26B-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Outlier-Ai/Outlier-Quick-26B-MLX-4bit 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 "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"

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 Outlier-Ai/Outlier-Quick-26B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Outlier-Ai/Outlier-Quick-26B-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Outlier-Ai/Outlier-Quick-26B-MLX-4bit"

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 "Outlier-Ai/Outlier-Quick-26B-MLX-4bit" \
  --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"

Part of the Outlier shipping lineup. Outlier is a free macOS app that runs this model locally, with one click. Apple Silicon only. Outlier for Mac: free Nano and Lite; Pro is $49 once, on up to 3 Macs · brew install --cask outlier-host/tap/outlier

Outlier Quick 26B (MLX 4-bit)

What this is: Gemma 4 26B-A4B (a mixture-of-experts, about 4B parameters active per token) converted to MLX 4-bit. Nothing else is changed: no fine-tune, no merge. It is the Quick tier of the Outlier app for Mac, which downloads exactly these files.

Download size: 15.61 GB · minimum unified memory: 16 GB · Apple silicon
Licence: Apache 2.0, the base model's licence. The Outlier team converted the weights; the model is the base model's authors' work.
In the app: part of Pro ($49 once)

Measured results

These are the figures on outlier.host, with how each was run. Small samples: at n=200 an MMLU figure can be off by up to 7 points either way.

Test	Result	How
MMLU	81.0% (162/200)	a 200-question sample, build 1.11.804, 2026-08-24
HumanEval	Not measured
SWE-bench Verified (agentic)	0% (0/50; all 50 patches empty), blind, build 1.11.788	a random 50-task sample (seed 42), no test patch or file hint
Decode speed, M1 Ultra	43.6 tok/s (median of 20 runs through the shipped 1.11.804 app, 2026-08-24)

The app you download is a later build than the one measured; these figures have not been re-run on it.

Use it

The easiest way is the Outlier app: pick Outlier Quick in the model picker and it downloads these files.

To load the weights yourself:

pip install mlx-lm
python -m mlx_lm.generate --model Outlier-Ai/Outlier-Quick-26B-MLX-4bit --prompt "Hello" --max-tokens 256

The other Outlier tiers

Outlier Nano 4B (free)
Outlier Lite 9B (free)
Outlier Core 27B (Pro)
Outlier Plus 397B (Qwen3.5-397B-A17B, a public community conversion) (Pro)
Outlier Vision 3.8 27B (Qwen3.8-27B, a public community conversion) (Pro)

Earlier experiments in this organisation (Outlier-10B, -40B, -70B, -150B and others) are research checkpoints. The app does not ship them.

Downloads last month: 66

Safetensors

Model size

26B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Evaluation results

accuracy on MMLU (200-question sample, build 1.11.804, 2026-08-24)
self-reported

0.810