Instructions to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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("nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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
LM Studio

Unsloth Studio new

How to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx",
    max_seq_length=2048,
)

Pi new

How to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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 "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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 "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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 nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx

Run Hermes

hermes

MLX LM

How to use nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-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 "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.503,0.640,0.861

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    4.685 ± 0.033   12.17 GB      563

Base model

granite-4.1-8b
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.486,0.666,0.875,0.636,0.450,0.766,0.631

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8   10.134 ± 0.107   12.17 GB      286

More metrics coming soon.

-G

granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx

This model granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx was converted to MLX format from DavidAU/granite-4.1-8b-Stone-Cold-Thinking using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

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

Downloads last month: 235

Safetensors

Model size

9B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx

DavidAU/granite-4.1-8b-Stone-Cold-Thinking

ibm-granite/granite-4.1-8b

Merge model

this model

Collections including nightmedia/granite-4.1-8b-Stone-Cold-Thinking-V1-mxfp8-mlx