Instructions to use mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT 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("mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT")

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 mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT"

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": "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT 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 "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT"

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 mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT

Run Hermes

hermes

MLX LM

How to use mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MLX-LM-LoRA Model

This model was fine-tuned using mlx-lm-lora version 2.1.0.

Model Details

Base model: allenai/Olmo-3-7B-Instruct
Model type: olmo3
Training method: QAT + LoRA fine-tuning with MLX
Fusion date: 2026-04-22 23:46:40

Usage

This model can be loaded and used with the MLX framework.

Command to recreate

python -m mlx_lm_lora.train \
--model allenai/Olmo-3-7B-Instruct \
--train-type lora \
--optimizer adamw \
--steps-per-report 1 \
--iters 100 \
--max-seq-length 4096 \
--adapter-path ./Olmo-3-7B-Instruct-mxfp4-QAT \
--data mlx-community/Dolci-Instruct-SFT-No-Tools-400K \
--train \
--qat-enable \
--qat-bits 4 \
--qat-group-size 64 \
--qat-mode mxfp4 \
--qat-start-step 1 \
--qat-interval 1

Downloads last month: 126

Safetensors

Model size

1B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT

Base model

allenai/Olmo-3-1025-7B

Finetuned

allenai/Olmo-3-7B-Instruct-SFT

Finetuned

allenai/Olmo-3-7B-Instruct-DPO

Finetuned

allenai/Olmo-3-7B-Instruct

Quantized

(37)

this model

mlx-community
/

Olmo-3-7B-Instruct-mxfp4-QAT

MLX-LM-LoRA Model

Model Details

Usage

Command to recreate

Model tree for mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT

Dataset used to train mlx-community/Olmo-3-7B-Instruct-mxfp4-QAT