Instructions to use OsaurusAI/LFM2.5-VL-3B-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/LFM2.5-VL-3B-MXFP8 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("OsaurusAI/LFM2.5-VL-3B-MXFP8")
config = load_config("OsaurusAI/LFM2.5-VL-3B-MXFP8")

# 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 OsaurusAI/LFM2.5-VL-3B-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-VL-3B-MXFP8"

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": "OsaurusAI/LFM2.5-VL-3B-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/LFM2.5-VL-3B-MXFP8 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 "OsaurusAI/LFM2.5-VL-3B-MXFP8"

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 OsaurusAI/LFM2.5-VL-3B-MXFP8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/LFM2.5-VL-3B-MXFP8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-VL-3B-MXFP8"

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 "OsaurusAI/LFM2.5-VL-3B-MXFP8" \
  --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"

LFM2.5-VL-3B-MXFP8 / README.md

Osaurus-AI

Add files using upload-large-folder tool

0229cf4 verified 6 days ago

preview code

Raw

History Blame Contribute Delete

4.82 kB

	---
	license: other
	license_name: lfm1.0
	license_link: https://huggingface.co/LiquidAI/LFM2.5-VL-3B/blob/main/LICENSE
	base_model: LiquidAI/LFM2.5-VL-3B
	base_model_relation: quantized
	library_name: mlx
	pipeline_tag: image-text-to-text
	tags:
	- mlx
	- vmlx-swift
	- osaurus
	- jang
	- liquid
	- lfm2.5
	- vision-language
	- multimodal
	language:
	- en
	- zh
	- ar
	---

	<p align="center"><a href="https://osaurus.ai"><img src="./osaurus-x-banner.png" alt="Osaurus AI"></a></p>

	# OsaurusAI/LFM2.5-VL-3B-MXFP8

	MX FP8 (`mx.quantize(mode="mxfp8")`, group size 32). Highest-fidelity bundle; use as the quality reference.

	MX FP8 (group size 32) conversion of [`LiquidAI/LFM2.5-VL-3B`](https://huggingface.co/LiquidAI/LFM2.5-VL-3B) for Apple silicon (MLX).

	LFM2.5-VL-3B is a vision-language model: a hybrid short-convolution +
	attention `lfm2` text backbone (30 layers, 22 conv / 8 full-attention) paired
	with a SigLIP2 `so400m-patch16-naflex` vision tower and a 2-layer projector.
	Images are tiled (up to 10 tiles at 512px) into 64–256 image tokens.

	## Bundles in this series

	\| Bundle \| Avg bits \| Size \| Notes \|
	\|---\|---\|---\|---\|
	\| [`LFM2.5-VL-3B-JANG_2L`](https://huggingface.co/OsaurusAI/LFM2.5-VL-3B-JANG_2L) \| 3.14 \| 1.9 GB \| smallest \|
	\| [`LFM2.5-VL-3B-JANG_4M`](https://huggingface.co/OsaurusAI/LFM2.5-VL-3B-JANG_4M) \| 4.12 \| 2.2 GB \| recommended \|
	\| [`LFM2.5-VL-3B-JANG_6M`](https://huggingface.co/OsaurusAI/LFM2.5-VL-3B-JANG_6M) \| 6.06 \| 2.9 GB \| near-lossless \|
	\| [`LFM2.5-VL-3B-MXFP8`](https://huggingface.co/OsaurusAI/LFM2.5-VL-3B-MXFP8) \| 9.31 \| 3.4 GB \| MX FP8 reference \|

	## The vision tower is not quantized

	All four bundles keep the 437 SigLIP2 vision tensors at source precision.
	Quantizing a vision tower aggressively is what breaks image understanding, so
	the bits are spent on the language model instead. This is why image quality
	holds up even in the smallest bundle — and why the small profiles are dominated
	by the tower rather than the LM.

	## Verified

	Loaded and generated on an M5 Max on 2026-08-12, through this bundle's own
	`chat_template.jinja` and `processor_config.json`:

	- Vision — correctly named both shapes, both colors and their positions on a
	synthetic probe image
	- Multi-turn — carried image context across three turns, including a
	follow-up comparison ("which is larger, and where") and a format constraint
	- Tool calling — parsed `<\|tool_call_start\|>[get_weather(city='...')]<\|tool_call_end\|>`
	into `{'name': 'get_weather', 'arguments': {'city': 'Santa Clara'}}`

	## Sampling

	LiquidAI's documented settings, stamped into both `generation_config.json`
	and `jang_config.json`:

	\| Parameter \| Value \|
	\|---\|---\|
	\| `temperature` \| 0.2 \|
	\| `top_k` \| 50 \|
	\| `top_p` \| 1.0 (disabled) \|
	\| `repetition_penalty` \| 1.0 \|
	\| `eos_token_id` \| `[124900]` \|

	`top_p` is not specified upstream, so it is stamped as disabled rather than
	invented.

	## Reasoning

	This model does not reason — it answers directly. There is no thinking rail:
	the chat template emits a bare `<\|im_start\|>assistant\n` generation prompt with
	no `<think>` prefill, and no `enable_thinking` / `thinking` / `preserve_thinking`
	kwarg changes it (verified byte-identical). `preserve_thinking` only governs
	whether `<think>` in prior assistant turns is retained, which is history
	handling. The bundle metadata says `supports_thinking: false` accordingly.

	## Usage

	```python
	from mlx_vlm import load, generate
	from mlx_vlm.prompt_utils import apply_chat_template

	model, processor = load("OsaurusAI/LFM2.5-VL-3B-MXFP8")
	messages = [{"role": "user", "content": "What is in this image?"}]
	prompt = apply_chat_template(processor, model.config, messages, num_images=1)
	print(generate(model, processor, prompt, image=["photo.jpg"],
	max_tokens=256, temperature=0.2, verbose=False))
	```

	## Notes for MLX runtimes

	This bundle carries three config keys the MLX stack needs that the upstream
	checkpoint does not provide in the expected form:

	- `text_config.block_ff_dim` — mlx_lm's `lfm2` requires it; without it the FFN
	dimension is computed wrong and the model fails to load.
	- `image_token_index` — mirrors upstream's `image_token_id`; mlx_vlm reads the
	`_index` spelling and otherwise matches zero image tokens.
	- per-module quantization overrides are emitted under both `model.<path>` and
	the post-sanitize `<path>` spelling, because mlx_vlm looks up the latter.

	`tool_parser_type: "pythonic"` is set explicitly so mlx_lm resolves the tool
	parser without relying on template string-matching.

	## License

	Released under the base model's license. Review
	[`LiquidAI/LFM2.5-VL-3B`](https://huggingface.co/LiquidAI/LFM2.5-VL-3B) terms before use.

	---

	Converted by Jinho Jang — <eric@osaurus.ai> — with [JANG](https://osaurus.ai).