Instructions to use meshllm/llama-3.2-1b-instruct-parity-bf16-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshllm/llama-3.2-1b-instruct-parity-bf16-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("meshllm/llama-3.2-1b-instruct-parity-bf16-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)

Inference
Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use meshllm/llama-3.2-1b-instruct-parity-bf16-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 "meshllm/llama-3.2-1b-instruct-parity-bf16-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": "meshllm/llama-3.2-1b-instruct-parity-bf16-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use meshllm/llama-3.2-1b-instruct-parity-bf16-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 "meshllm/llama-3.2-1b-instruct-parity-bf16-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 meshllm/llama-3.2-1b-instruct-parity-bf16-mlx

Run Hermes

hermes

MLX LM

How to use meshllm/llama-3.2-1b-instruct-parity-bf16-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 "meshllm/llama-3.2-1b-instruct-parity-bf16-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "meshllm/llama-3.2-1b-instruct-parity-bf16-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "meshllm/llama-3.2-1b-instruct-parity-bf16-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Llama 3.2 1B Instruct Parity BF16 MLX

Same-origin MLX artifact for mesh-llm parity testing.

Source checkpoint: meta-llama/Llama-3.2-1B-Instruct
Conversion path: original checkpoint -> MLX bf16
Intended pair: meshllm/llama-3.2-1b-instruct-parity-f16-gguf

Validation

Validated locally with the mesh-llm exact smoke suite on 2026-04-06.

Expected behavior for this pair:

Shared strict lowercase drift on blue/green/red
Clean agreement on the remaining exact prompts

Files

MLX model directory contents

Downloads last month: 23

Safetensors

Model size

1B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for meshllm/llama-3.2-1b-instruct-parity-bf16-mlx

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1747)

this model