SAM3 now runs offline on your GPU: ONNX export hits 0.37s on M5, 0.08s on RTX 3080 Ti
CSProfKGD · x · 2026-10-30
An ONNX export of Meta's SAM3 now runs fully offline on NVIDIA CUDA and Apple CoreML.
Beyond text prompts, it accepts example boxes, negative boxes, and clicks as prompts. Benchmarks show a text prompt takes about 0.37s on an M5 MacBook Pro and 0.08s on an RTX 3080 Ti.
More from Infra
- Anthropic eyes $2T valuation on $100B raise, with $431B compute commitments and circular vendor financing — LexSokolin · 2026-10-30
- Cloudflare private origins goes GA: WAF and caching for internal APIs and MCP servers — Cloudflare Blog · 2026-10-30
- Pika H3 Flex ported to Mac via MLX: 5s video in ~5 minutes on M4 Max — Opening-Ad5541 · 2026-10-30
- FlashAttention-2 v2.9.2 Windows wheels released for PyTorch 2.15.0+cu134 — Zestyclose_Bake3680 · 2026-10-30
- AgentX benchmark: lossless-CSF hits 11.4M KV cache tokens, 8.7x DeepSeek V4.1 Flash baseline — TheZachMueller · 2026-10-30
- 'Girls only want one thing': an $496,639 8x NVIDIA B300 deep learning server — Kyrannio · 2026-10-30