mlx-community/UI-Venus-1.5-8B-6bit

UI-Venus-1.5-8B 6bit

This is a 6-bit quantized MLX conversion of inclusionAI/UI-Venus-1.5-8B, optimized for Apple Silicon.

UI-Venus-1.5 is a unified end-to-end GUI agent family built for grounding, web navigation, and mobile navigation. The 1.5 family spans dense 2B and 8B variants plus a 30B-A3B MoE variant, and is framed upstream around a shared GUI semantics stage, online RL for long-horizon navigation, and model merging across grounding, web, and mobile domains.

This artifact was derived from the validated local MLX bf16 reference conversion and then quantized with mlx-vlm. It was validated locally with both mlx_vlm prompt-packet checks and vllm-mlx OpenAI-compatible serve checks.

Conversion Details

Field	Value
Upstream model	inclusionAI/UI-Venus-1.5-8B
Artifact type	6bit quantized MLX conversion
Source artifact	local validated bf16 MLX artifact
Conversion tool	mlx_vlm.convert via mlx-vlm 0.3.12
Python	3.11.14
MLX	0.31.0
Transformers	5.2.0
Validation backend	vllm-mlx (phase/p1 @ 8a5d41b)
Quantization	6bit
Group size	64
Quantization mode	affine
Converter dtype note	float16
Reported effective bits per weight	7.125
Artifact size	7.28G
Template repair	tokenizer_config.json["chat_template"] was re-injected after quantization

Additional notes:

• This MLX artifact preserves the dual-template contract across chat_template.json, chat_template.jinja, and tokenizer_config.json["chat_template"].
• chat_template.jinja is present as an additive compatibility shim.
• No manual dtype edit was applied after conversion.

Validation

This artifact passed local validation in this workspace:

• mlx_vlm prompt-packet validation: PASS
• vllm-mlx OpenAI-compatible serve validation: PASS

Local validation notes:

• output stayed in the same behavior envelope as the local bf16 reference artifact
• schema stayed valid on the structured-action prompt and retained the requested reason field
• grounding drifted modestly lower/right relative to bf16, but still pointed at the correct API Host region

Performance

• Artifact size on disk: 7.28G
• Local fixed-packet mlx_vlm validation used about 20.82 GB peak memory
• Observed local fixed-packet throughput was about 183-189 prompt tok/s and 40.7-51.9 generation tok/s across the four validation prompts
• Local vllm-mlx serve validation completed in about 25.18s non-stream and 26.84s streamed

These are local validation measurements, not a full benchmark suite.

Usage

Install

pip install -U mlx-vlm

CLI

python -m mlx_vlm.generate \
  --model mlx-community/UI-Venus-1.5-8B-6bit \
  --image path/to/image.png \
  --prompt "Describe the visible controls on this screen." \
  --max-tokens 256 \
  --temperature 0.0

Python

from mlx_vlm import load, generate

model, processor = load("mlx-community/UI-Venus-1.5-8B-6bit")
result = generate(
    model,
    processor,
    prompt="Describe the visible controls on this screen.",
    image="path/to/image.png",
    max_tokens=256,
    temp=0.0,
)
print(result.text)

vllm-mlx Serve

python -m vllm_mlx.cli serve mlx-community/UI-Venus-1.5-8B-6bit --mllm --localhost --port 8000

Links

• Upstream model: inclusionAI/UI-Venus-1.5-8B
• Paper: UI-Venus-1.5 Technical Report
• Paper: UI-Venus Technical Report: Building High-performance UI Agents with RFT
• GitHub: inclusionAI/UI-Venus
• MLX framework: ml-explore/mlx
• mlx-vlm: Blaizzy/mlx-vlm

Other Quantizations

Planned sibling repos in this wave:

• mlx-community/UI-Venus-1.5-8B-bf16
• mlx-community/UI-Venus-1.5-8B-6bit - this model
• mlx-community/UI-Venus-1.5-8B-4bit

Notes and Limitations

• This card reports local MLX conversion and validation results only.
• Upstream benchmark claims belong to the original UI-Venus model family and were not re-run here unless explicitly stated.
• Quantization changes numerical behavior relative to the local bf16 reference artifact.
• The main qualitative change relative to bf16 was modest grounding drift, not schema breakage or text collapse.

Citation

If you use this MLX conversion, please cite the original UI-Venus papers:

• UI-Venus-1.5 Technical Report
• UI-Venus Technical Report: Building High-performance UI Agents with RFT

License

This repo follows the upstream model license: Apache 2.0. See the upstream model card for the authoritative license details: inclusionAI/UI-Venus-1.5-8B.