Miril-DroneVLM-2B-2-MLX-8bit

Miril-DroneVLM-2B-2-MLX-8bit

The balanced Apple Silicon edition of Miril-DroneVLM-2B-2

Drones can talk.

This repository contains the 8-bit MLX-VLM deployment variant of Miril-DroneVLM-2B-2, Miril.ai's open-weight aerial VLM. Give it an overhead image and an ordinary question such as “What am I looking at?”, “Any people?”, “Choose a place for this parcel,” or “Track the white car.” It returns typed JSON that identifies how the answer should be interpreted.

This is the same four-route model interface as the merged checkpoint, converted for Apple Silicon. See the primary model card for the caption, answer, location, and pointing responses, fixed system contract, precise-point and coarse-direction rules, runnable validation code, WALDO lineage, limitations, and safety requirements.

Methods and citation: Miril-DroneVLM-2B-2: Turning Aerial Detector Labels into a Structured Vision-Language Interface.

Deployment Profile

<!-- MIRIL_VARIANT_PROFILE_START -->

• Artifact size: 5.49 GiB
• Recommended starting envelope: 8.5 GiB free unified memory
• Estimate covers model weights plus practical single-image runtime headroom; larger images, batching, long generations, and server overhead need more.

<!-- MIRIL_VARIANT_PROFILE_END -->

Use this variant when you want lower Apple unified-memory use while retaining more weight precision than the 4-bit path. The deployment profile reports measured artifact size, a recommended memory envelope, and full same-case quality deltas.

Run It

python -m pip install mlx-vlm huggingface_hub pillow
hf download MirilAI/Miril-DroneVLM-2B-2 mlx_inference.py inference.py router_contract.py --local-dir miril-drone-runtime
python miril-drone-runtime/mlx_inference.py \
  --model-id MirilAI/Miril-DroneVLM-2B-2-MLX-8bit \
  --image drone_frame.jpg \
  --prompt "What am I looking at?"

The helper applies the same fixed system prompt and strict response validator as the CUDA path. Invalid or contradictory coordinates are never returned as dispatch-safe points.

Export Integrity

Gemma 4 E2B uses shared key/value layers. The included shared-KV export audit verifies the expected tensor-owner layout for this exact MLX artifact; the absence of separate k_proj, v_proj, and k_norm tensors on sharing layers is intentional.

Complete Benchmark

<!-- MIRIL_RELEASE_METRICS_START -->

Complete held-out validation

Cleaned held-out deployment audit

After training, a stricter held-out audit removed pointing rows whose targets fall below the model-visible size threshold, then ran every release artifact on the complete revised validation and test splits. Strict-cleaned rows use only accepted evidence. Coverage-matched rows add evidence-preserving questions on the same held-out images to restore the earlier route and pointing action/status mix; they do not recreate the earlier object-class histogram.

Final held-out test

Strict-cleaned evidence

Coverage-matched evidence

Validation

Strict-cleaned evidence

Coverage-matched evidence

Validation supports comparison and model selection; test is the final held-out report. These automated scores measure contract and reference agreement, not flight safety.

Spoken-query results on the primary model card apply to the merged BF16 checkpoint. This deployment variant has not inherited that claim without a separate matched audio evaluation.

The merged and deployment variants use identical cases within each evaluation. Automated scores are regression signals, not safety certification.

<!-- MIRIL_RELEASE_METRICS_END -->

The tables below compare MLX and CUDA artifacts on identical complete held-out validation and test cases. Partial runs are excluded. Automated scores are regression signals, not safety certification.

Limits And Safety

This is a research perception model, not a flight controller or certified safety system. Follow the complete limitations and operational guidance on the primary model card.

License

Apache License 2.0. See LICENSE and NOTICE.