← All hardware
In-memory compute edge accelerator: 214 TOPS at 14.7 TOPS/W
Pros
- Excellent efficiency
- Strong TOPS for edge
- Flexible form factors
- Good for multi-stream vision
Cons
- Inference-only
- INT8-centric (limited GenAI)
- Smaller ecosystem
- Vision-focused
✓ Where it shines / best for
- Edge computer vision
- Smart cameras/retail
- Industrial inspection
- Multi-stream inference
✕ Not the best fit for
- Training
- Large LLM inference
- CUDA workflows
- Datacenter scale
Features
- ✓ Digital in-memory compute (D-IMC)
- ✓ 214 TOPS peak INT8
- ✓ 14.7 TOPS/W efficiency
- ✓ M.2 (1GB DRAM) or PCIe
- ✓ Quad-core MVM accelerator
- ✓ Voyager SDK
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| Metis M.2 / PCIe | ~$150-$500 | one-time | Form-factor dependent; via channel |
Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.
Specifications
| use | Edge vision inference |
| power | ~Few watts to ~tens of watts |
| memory | 1GB+ DRAM on module |
| performance | 214 TOPS INT8, 14.7 TOPS/W |
| architecture | Digital in-memory compute (quad-core) |
Sponsored
A full review is being generated for this product and will appear here shortly.