runanywhere/Fara1.5-4B-mlx-4bit

Fara1.5-4B — MLX 4-bit

An Apple MLX 4-bit conversion of microsoft/Fara1.5-4B, Microsoft AI Frontiers' agentic Computer-Use Agent (CUA) for web browsers, built on the Qwen3.5-VL architecture (model_type: qwen3_5 / qwen3_5_vision).

This repository only re-packages Microsoft's model for on-device Apple-silicon inference. All model capabilities, training, and credit belong to Microsoft AI Frontiers. Original model, full system prompt, and the MagenticLite agent scaffold: https://huggingface.co/microsoft/Fara1.5-4B and https://github.com/microsoft/fara.

What this is

• Format: MLX, 4-bit (affine, group size 64). The vision tower is kept at full precision (bf16) — only the language-model layers are quantized — so visual grounding is not degraded by quantization.
• Size: ~3.7 GB (vs ~8 GB bf16).
• Converted with mlx-vlm 0.6.6:

  python -m mlx_vlm convert --hf-path microsoft/Fara1.5-4B \
    --mlx-path Fara1.5-4B-mlx-4bit -q
  

Usage

Loads through MLX VLM stacks that support qwen3_5 (e.g. mlx-vlm, and mlx-swift-lm's Qwen35 VLM class) with no code changes.

python -m mlx_vlm generate --model runanywhere/Fara1.5-4B-mlx-4bit \
  --image screenshot.png --system "$FARA_SYSTEM_PROMPT" \
  --prompt "Book a table for 2 at a sushi place in Sunnyvale for Friday 7pm." \
  --temperature 0.0 --max-tokens 1024

Fara is a web-browser agent. To drive it correctly, use Microsoft's contract (see the base model / microsoft/fara):

• Provide the full system prompt including the computer_use tool schema inside <tools></tools> — without it the model cannot reliably emit valid tool-calls.
• The model emits actions as <tool_call>{"name": "computer_use", "arguments": {...}}</tool_call>.
• Coordinates are returned in a fixed 1000×1000 space; scale to your viewport (e.g. x*1.44, y*0.9 for a 1440×900 window). 1440×900 is the recommended capture size.
• The reference agent loop, safety "critical points", and sandboxing live in MagenticLite.

Validation

Verified running through the Apple MLX runtime (Python mlx-vlm and Swift mlx-swift-lm). On a small suite of real 1440×900 browser screenshots with Fara's exact CUA prompt, this 4-bit conversion produced valid left_click tool-calls and grounded coordinates that were near-identical (within ~0.1–0.3%) to the full-precision f32 reference on every task, missing the same targets with the same coordinates — i.e. the quantization is essentially lossless; any grounding errors are the base model's own behavior, not an artifact of this conversion.

License

MIT, inherited from microsoft/Fara1.5-4B. Please review Microsoft's model card for intended use, limitations, and responsible-AI guidance (Fara is trained to pause at safety-critical points; keep a human in the loop for irreversible actions).