FocsleFocsle
Fo’c’sle

DINO-v3-Distilled

21%
by Fo’c’sle

Distilled DINO-v3 backbone for downstream perception. The encoder under most of our reference models.

MultimodalFocsle-ResearchINT8FP16backbonessldino
64K downloads 2.4K deploymentsUpdated Apr 12, 2028
Headline:14.8ms · NVIDIA Jetson Orin Nano · FP16

Cross-chip benchmark matrix

Every supported chip, in matched-pair runs from the Fo’c’sle HIL lab. Sortable by any column — click a header. Cells where the chip can’t run this model show Not supported.

Chip platformQuantLatency p50(ms)Latency p95(ms)ThroughputAcc. retention(%)Power(W)Memory(MB)Tested by
N
NVIDIA Jetson Thor
2070 TOPS · Module
FP1618.223.755 FPS99.8122.3204Fo’c’sle HIL
N
NVIDIA Jetson AGX Orin
275 TOPS · Module
FP1626.133.638 FPS99.755.4204Fo’c’sle HIL
Q
Snapdragon 8 Gen 3 NPU
45 TOPS · SoC
INT838.245.826 FPS98.46.4102Fo’c’sle HIL
Q
Qualcomm QCS8550
48 TOPS · SoC
INT853.464.019 FPS98.514.1102Fo’c’sle HIL
N
NVIDIA Jetson Orin Nano
40 TOPS · SoM
INT863.680.316 FPS97.412.6102Fo’c’sle HIL
Apple Neural Engine (M4)
38 TOPS · SoC
FP1678.199.513 FPS99.87.1204Fo’c’sle HIL
H
Hailo-8
26 TOPS · M.2
Not supported
H
Hailo-10H
40 TOPS · M.2
Not supported
Q
Qualcomm QCS6490
12 TOPS · SoC
Not supported
π
Raspberry Pi 5 + Hailo HAT
26 TOPS · HAT
Not supported
A
Ambarella CV5
16 TOPS · SoC
Not supported
A
Ambarella CV72
32 TOPS · SoC
Not supported
M
MediaTek Genio 700
4 TOPS · SoC
Not supported
G
Google Coral Edge TPU
4 TOPS · USB
Not supported
I
Intel Movidius Myriad X
4 TOPS · SoC
Not supported
A
AMD Versal AI Edge VE2302
22 TOPS · SoC
Not supported
R
Rockchip RK3588
6 TOPS · SoC
Not supported
Leader per columnMS-COCO captions · 224×224 image / 32-token text

HIL conditions

All numbers measured on Fo’c’sle HIL rigs in Tel Aviv (primary), Munich (secondary), and Pittsburgh (robotics). Single-stream, batch-1, real preprocessing, real downstream consumer. p50/p95 are over 10,000-frame steady-state windows after a 30-second warm-up. Power draw is package power, not wall power. Memory footprint is the resident model + activations footprint at peak — not on-disk.

Submitted publisher numbers are accepted only if they reproduce within ±8% of an HIL-lab matched run on the same chip in the same input mode. Otherwise they live separately under the Discussion tab.