Instructions to use mlx-community/Agents-A1-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Agents-A1-bf16 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("mlx-community/Agents-A1-bf16")
config = load_config("mlx-community/Agents-A1-bf16")

# 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 mlx-community/Agents-A1-bf16 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/Agents-A1-bf16"

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/Agents-A1-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Agents-A1-bf16 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/Agents-A1-bf16"

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/Agents-A1-bf16

Run Hermes

hermes

OpenClaw new

How to use mlx-community/Agents-A1-bf16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Agents-A1-bf16"

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 "mlx-community/Agents-A1-bf16" \
  --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"

gabfssilva commited on 17 days ago

Commit

d4135c3

verified ·

1 Parent(s): a13eccf

Card: simplify conversion notes (oQ→mlx-vlm rationale)

Browse files

Files changed (1) hide show

README.md +0 -6

README.md CHANGED Viewed

@@ -30,12 +30,6 @@ python -m mlx_vlm.generate --model mlx-community/Agents-A1-bf16 --image img.jpg
 Loads and runs in **stock mlx-vlm** — no patched code needed at inference.
-## Conversion notes
-Upstream ships its MoE experts **unfused / per-expert** (`...mlp.experts.{i}.{gate,up,down}_proj.weight`, 256 experts x 40 layers). mlx-vlm's stock `qwen3_5_moe` converter expects the **fused** layout (`experts.gate_up_proj`) of the official Qwen3.5 release, so it fails on this checkpoint with `KeyError: ...experts.gate_up_proj`.
-This build was produced by patching mlx-vlm's `sanitize()` to stack the per-expert tensors into the batched `switch_mlp.{gate,up,down}_proj` layout MLX uses (the same transform mlx-lm applies to Qwen3-MoE), then saved as standard MLX. The patch is **conversion-only** — the published weights load in stock mlx-vlm.
 ## Throughput
 Measured with oMLX's benchmark harness on a Macbook Pro M5 Max 128GB 40 GPU — gen 128 tokens,

 Loads and runs in **stock mlx-vlm** — no patched code needed at inference.
 ## Throughput
 Measured with oMLX's benchmark harness on a Macbook Pro M5 Max 128GB 40 GPU — gen 128 tokens,