Fara1.5-4B โ€” 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) โ€” only the language-model layers are quantized โ€” 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> โ€” 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 1000ร—1000 space; scale to your viewport (e.g. x*1.44, y*0.9 for a 1440ร—900 window). 1440ร—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 1440ร—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 ~0.1โ€“0.3%) to the full-precision f32 reference on every task, missing the same targets with the same coordinates โ€” 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).

Downloads last month
34
Safetensors
Model size
5B params
Tensor type
U32
ยท
F32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for runanywhere/Fara1.5-4B-mlx-4bit

Finetuned
Qwen/Qwen3.5-4B
Quantized
(11)
this model