Instructions to use nightmedia/granite-4.1-8b-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-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 Settings
LM Studio

Unsloth Studio

How to use nightmedia/granite-4.1-8b-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-mxfp8-mlx",
    max_seq_length=2048,
)

How to use nightmedia/granite-4.1-8b-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-mxfp8-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nightmedia/granite-4.1-8b-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-mxfp8-mlx

Run Hermes

hermes

MLX LM

How to use nightmedia/granite-4.1-8b-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-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-Fred-Flintstone-mxfp8-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

nightmedia commited on May 5

Commit

0641118

verified ·

1 Parent(s): bc23d75

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -37,6 +37,8 @@ Brainwaves
 bf16     0.527,0.700,0.865,0.659,0.428,0.763,0.684
 mxfp8    0.520,0.710,0.864,0.668,0.420,0.771,0.659
 mxfp4    0.503,0.652,0.863,0.652,0.418,0.761,0.654
 Quant    Perplexity      Peak Memory   Tokens/sec
 bf16     4.257 ± 0.030   20.58 GB      709

 bf16     0.527,0.700,0.865,0.659,0.428,0.763,0.684
 mxfp8    0.520,0.710,0.864,0.668,0.420,0.771,0.659
 mxfp4    0.503,0.652,0.863,0.652,0.418,0.761,0.654
+qx64-hi  0.526,0.702,0.859,0.649,0.428,0.770,0.677
 Quant    Perplexity      Peak Memory   Tokens/sec
 bf16     4.257 ± 0.030   20.58 GB      709