Instructions to use lthn/lemrd-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lthn/lemrd-mlx-8bit with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("lthn/lemrd-mlx-8bit")
config = load_config("lthn/lemrd-mlx-8bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use lthn/lemrd-mlx-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lthn/lemrd-mlx-8bit"

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": "lthn/lemrd-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use lthn/lemrd-mlx-8bit 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 "lthn/lemrd-mlx-8bit"

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 lthn/lemrd-mlx-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lthn/lemrd-mlx-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lthn/lemrd-mlx-8bit"

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 "lthn/lemrd-mlx-8bit" \
  --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"

lemrd-mlx-8bit

Commit History

Apr 17

08:01
fix(config): sync with upstream Google Gemma 4 day-1 fixes (b446025, b4a6011)⁠

lthn

Verified signature
88b4e90

Apr 11

19:08
docs: correct base_model lineage for HF model tree⁠

Snider +1: Virgil

d31df73

Apr 10

19:30
feat: merge LEK into lemrd weights⁠

Snider +1: Virgil

826e60a
03:12
fix: pull Google's chat_template.jinja fix (26B/31B variant)⁠

Snider +1: Cladius Maximus

4407e16
01:08
fix: replace LICENSE symlink with real EUPL-1.2 file⁠

Snider +1: Cladius Maximus

7f0ef4d

Apr 9

20:46
fix: exact configs from unsloth 31b-8bit reference⁠

Snider +1: Cladius Maximus

d51392e
12:57
Upload config.json with huggingface_hub

lthn

Verified signature
4af73c7
12:21
Upload tokenizer_config.json with huggingface_hub

lthn

Verified signature
e539a3a
12:21
Upload config.json with huggingface_hub

lthn

Verified signature
7b26f19
12:06
Upload processor_config.json with huggingface_hub

lthn

Verified signature
0e8f8a8
11:52
Upload config.json with huggingface_hub

lthn

Verified signature
a4314e3
11:50
Upload folder using huggingface_hub

lthn

Verified signature
54958a0
11:30
initial commit

lthn

Verified signature
80f7dd9

Commit History

Apr 17

fix(config): sync with upstream Google Gemma 4 day-1 fixes (b446025, b4a6011)⁠

Apr 11

docs: correct base_model lineage for HF model tree⁠

Apr 10

feat: merge LEK into lemrd weights⁠

fix: pull Google's chat_template.jinja fix (26B/31B variant)⁠

fix: replace LICENSE symlink with real EUPL-1.2 file⁠

Apr 9

fix: exact configs from unsloth 31b-8bit reference⁠

Upload config.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload processor_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload folder using huggingface_hub

initial commit