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"

Agents-A1-bf16 / README.md

gabfssilva

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

d4135c3 verified 17 days ago

preview code

Raw

History Blame Contribute Delete

3.42 kB

	---
	base_model: InternScience/Agents-A1
	library_name: mlx
	pipeline_tag: image-text-to-text
	license: apache-2.0
	tags:
	- mlx
	- vision-language
	- moe
	- agent
	---

	# Agents-A1 — MLX (bf16)

	[MLX](https://github.com/ml-explore/mlx) conversion of [InternScience/Agents-A1](https://huggingface.co/InternScience/Agents-A1), in bf16. The source checkpoint is already bf16, so this is a lossless format conversion — not a quantization.

	Agents-A1 is a Qwen3.5-MoE vision-language agent model (`qwen3_5_moe`, `Qwen3_5MoeForConditionalGeneration`): 40 decoder layers, 256 routed experts per layer + a shared expert, hidden size 2048, with a vision tower and video preprocessing.

	## Running it

	Multimodal (VLM) — load with mlx-vlm (mlx-lm can't load multimodal architectures):

	```bash
	pip install mlx-vlm
	python -m mlx_vlm.generate --model mlx-community/Agents-A1-bf16 \
	--prompt "What is 17 * 24? Think step by step." --max-tokens 512
	# with an image:
	python -m mlx_vlm.generate --model mlx-community/Agents-A1-bf16 --image img.jpg --prompt "Describe this image."
	```

	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,
	cold prefill (unique prompt prefix per request, no cache reuse).

	### Single request (batch 1) — decode tok/s by context

	\| Context \| bf16 \| 8-bit \| 6-bit \| 5-bit \| 4-bit \| 3-bit \|
	\|--------:\|-----:\|------:\|------:\|------:\|------:\|------:\|
	\| 1,024 \| 67.6 \| 95.4 \| 95.2 \| 98.2 \| 117.4 \| 133.0 \|
	\| 4,096 \| 67.6 \| 94.0 \| 97.3 \| 102.8 \| 119.5 \| 130.4 \|
	\| 8,192 \| 66.8 \| 91.7 \| 95.3 \| 103.1 \| 115.7 \| 126.9 \|
	\| 16,384 \| 64.7 \| 88.0 \| 91.5 \| 80.5 \| 105.8 \| 119.8 \|
	\| 32,768 \| 60.9 \| 80.6 \| 88.6 \| 80.2 \| 95.6 \| 104.2 \|
	\| 65,536 \| 53.5 \| 68.4 \| 67.6 \| 66.6 \| 75.4 \| 83.5 \|
	\| 131,072 \| 40.7 \| 48.7 \| 50.9 \| 48.2 \| 50.3 \| 52.5 \|
	\| Peak RAM (GB) \| 66–69 \| 35–39 \| 27–31 \| 23–26 \| 19–22 \| 15–18 \|

	TTFT (cold prefill) is ~precision-independent — ≈0.3 s @1k, 3 s @8k, 21 s @32k, 63 s @64k,
	~225 s @128k — prefill is compute-bound, not weight-bound.

	### Continuous batching (1k context) — aggregate decode tok/s

	\| Batch \| bf16 \| 8-bit \| 6-bit \| 5-bit \| 4-bit \| 3-bit \|
	\|------:\|-----:\|------:\|------:\|------:\|------:\|------:\|
	\| 1 \| 67.6 \| 95.4 \| 95.2 \| 98.2 \| 117.4 \| 133.0 \|
	\| 2 \| 62.5 \| 151.0 \| 156.5 \| 160.6 \| 190.9 \| 188.7 \|
	\| 4 \| 107.1 \| 202.0 \| 185.1 \| 195.7 \| 239.9 \| 230.2 \|
	\| 8 \| 129.6 \| 252.4 \| 223.4 \| 238.7 \| 289.0 \| 276.1 \|

	Aggregate across the batch; per-request rate is that value divided by the batch size.

	## Smoke test

	`17 x 24` -> correct (`408`), coherent, no repetition.

	## Other precisions

	\| Precision \| Repo \| Size on disk \|
	\|---\|---\|---\|
	\| bf16 (full) \| [Agents-A1-bf16](https://huggingface.co/mlx-community/Agents-A1-bf16) \| ~65 GB \|
	\| 8-bit \| [Agents-A1-8bit](https://huggingface.co/mlx-community/Agents-A1-8bit) \| ~35 GB \|
	\| 6-bit \| [Agents-A1-6bit](https://huggingface.co/mlx-community/Agents-A1-6bit) \| ~27 GB \|
	\| 5-bit \| [Agents-A1-5bit](https://huggingface.co/mlx-community/Agents-A1-5bit) \| ~23 GB \|
	\| 4-bit \| [Agents-A1-4bit](https://huggingface.co/mlx-community/Agents-A1-4bit) \| ~19 GB \|
	\| 3-bit \| [Agents-A1-3bit](https://huggingface.co/mlx-community/Agents-A1-3bit) \| ~15 GB \|

	## License

	apache-2.0, inherited from the base model.