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

metadata

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 conversion of 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):

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	~65 GB
8-bit	Agents-A1-8bit	~35 GB
6-bit	Agents-A1-6bit	~27 GB
5-bit	Agents-A1-5bit	~23 GB
4-bit	Agents-A1-4bit	~19 GB
3-bit	Agents-A1-3bit	~15 GB

License

apache-2.0, inherited from the base model.