Google Coral SOM System-On-Modules
Bottom line: Per its Amazon listing, the Google Coral SOM System-On-Modules: 22.00 x 80.00 x 2.35 mm.
As an Amazon Associate, SpecPicks earns from qualifying purchases. Full disclosure →
Pros & Cons
Pros
- ✓ Connector M.2-2280-B-M-S3 (B/M Key)
- ✓ Backed by Google Coral's warranty and support channels
Cons
- ✗ Confirm socket / form-factor / power-rating compatibility against your build before ordering
- ✗ Price, stock, shipping and returns are set by the retailer and may have changed since this page was last updated
Manufacturer description
Performs high-speed ML inferencing The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at 400 FPS, in a power efficient manner. See more performance benchmarks. Works with Debian Linux Integrates with any Debian-based Linux system with a compatible card module slot. Supports TensorFlow Lite No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge…
SpecPicks Verdict
SpecPicks has no buyer-rating or benchmark data for Google Coral SOM System-On-Modules, so this read rests on the manufacturer's listed specs (how we evaluate). Compare with similarly-priced alternatives in the ai accelerators category before committing. Judge it on the specification table and the price rather than on sentiment: check the figures that decide your use case, then put it side-by-side with two or three close alternatives in the Compare tool before clicking through.
Common buyer scenarios for ai accelerators of this kind: matching it to an existing build, replacing a failing part, or upgrading from a previous-generation equivalent. Check the spec table below against your current setup — particularly socket / form-factor / power-rating fields — and confirm compatibility on the retailer's listing before purchase. Prices and stock are set by the retailer and may have moved since this page was last updated.
Key Features
Quoted from the manufacturer's listing. Where it differs from the pros and cons above, those note the conditions the listing leaves out.
- Connector M.2-2280-B-M-S3 (B/M Key)
- Google Edge TPU coprocessor
- 22.00 x 80.00 x 2.35 mm
- Supports TensorFlow Lite
- Works with Debian Linux
Full Specifications
| ASIN | B08BR3C21M |
|---|---|
| Brand | Google Coral |
| Item Weight | 0.317 ounces |
| Manufacturer | Google Coral |
| Product Dimensions | 2 x 2 x 1 inches |
| Date First Available | January 2, 2020 |
| Full listing title | SOM System-On-Modules - SOM Google Edge TPU ML Compute Accelerator, Integrate The Edge TPU into Legacy and New Systems Using a Standard M.2-2280-B-M-S3 (B/M Key) |
Benchmark data for other graphics cards
Ready to buy?
SOM System-On-Modules - SOM Google Edge TPU ML Compute Accelerator, Integrate The Edge TPU into Legacy and New Systems Using a Standard M.2-2280-B-M-S3 (B/M Key) is listed on Amazon. Price, availability, shipping and returns are set by Amazon and its sellers — check the listing for current terms. SpecPicks earns a small commission on qualifying purchases — thank you for supporting independent review work.
Related AI Accelerators
More guides & deep dives from the SpecPicks archive
Browse all articles & guides →- Best Budget Gaming PC Build 2026 — ~$1,000 Parts List
- Best Retro Handhelds in 2026: Pocket, Mid-Tier and FPGA Picks
- How to Build a Windows 98 Retro PC in 2026
- RTX 4070 Super vs RX 7800 XT — Which to Buy in 2026
- Emulation Hardware in 2026: FPGA, Software, and Cart-Reader Ecosystems
- The Complete Voodoo5 5500 AGP Driver Guide (2026 Edition)
- Best 1440p Gaming GPUs in 2026
More reviews from the SpecPicks archive
Browse all reviews →- Pro-Level 180Hz 1440p Gaming Monitor for $159: Gigabyte Deal
- Best Budget 1080p Gaming PC Parts in 2026: 5 Picks
- Crucial BX500 vs SanDisk SSD Plus vs WD Blue: Best Budget SATA SSD for a Boot Drive
- Logitech G29 vs HORI Force Feedback: Which Sim Wheel for Beginners?
- Best GPU for Ryzen 7 9800X3D in 2026: Pairing Guide
- AMD Ryzen AI Max+ 395 vs Mac Studio M4 Max for Local LLM Inference
- AI Coding Agents Find the Right File but Miss the Lines — What Local Code Models on a 12GB GPU Get Wrong
- Best SATA SSD for the PS4 Pro in 2026 (Cheap Speed Upgrade)
- Putting a Modern SATA SSD in a Win98/XP Retro Build via an IDE Bridge
- GLM-5.2: Probably the Most Powerful Text-Only Open-Weights LLM
- RTX 5090 vs RTX 4090 — is the Blackwell upgrade worth it?
- Best 4K Monitor for PS5 (4K/120Hz) in 2026
- DFlash Speculative Decoding on Qwen3.5-35B-A3B: How an RTX 2080 Super 8GB Hits 60+ tok/s
- pxpipe Hides Prompts in PNGs to Cut Claude Code Tokens 70% — Or Just Run Local on an RTX 3060
- Blue Yeti vs HyperX QuadCast 2 S: Which USB Mic Wins for Streaming in 2026?
- OpenAI Buys Ona: What Autonomous Codex Means for Local Coding Rigs
- 3dfx Voodoo2 SLI in 2026: Building a Period-Correct Windows 98 Glide Rig
- Qwen 3.6 27B vs Gemma 4 31B Local Inference: VRAM, Tok/s, and Quality Across Quantizations
- CPU Cooler Bracket Fix: How to Secure Your CPU When It Fails
- Best CPU Cooler for Ryzen 7 5800X and 5700X in 2026
- Logitech G29 vs HORI Racing Wheel Overdrive for Entry Sim Racing
- Intel-Scaler vLLM 0.21.0: What Changes for Local Arc + Intel GPU Rigs
- Best Gaming Mouse Pad for FPS Esports (2026)
- NVIDIA RTX PRO 6000 Blackwell vs RTX A6000: Is 96 GB Worth $4,000 More?
Earliest SpecPicks reviews
Browse full archive →- Best GPU for Llama 3.1 8B (2026)
- Best GPU for Qwen 3 14B (2026)
- Best GPU for Qwen 3 32B (2026)
- Best GPU for Llama 3.1 70B (2026)
- Best GPU for DeepSeek-R1 32B (2026)
- Best GPU for Llama 3.1 405B (2026)
- How to run Llama 3.1 8B on NVIDIA GeForce RTX 5090
- How to run Qwen 3 14B on NVIDIA GeForce RTX 5090
- How to run Qwen 3 32B on NVIDIA GeForce RTX 5090
- How to run Llama 3.1 70B on NVIDIA GeForce RTX 5090
- How to run DeepSeek-R1 32B on NVIDIA GeForce RTX 5090
- How to run Llama 3.1 8B on NVIDIA GeForce RTX 4090