ALPHA-One
The ALPHA-One is a Generative 7b LLM AI Agent based on StarPro64 board RISC-V based Single Board Computer with 20TOPS(int 8) NPU capability, and preinstalled 64G eMMC module contains 7b Deepseek/Owen LLM build in docker form.
Software releases
This is the production release build 20250627
DD image for 64GB eMMC module
- This build contains 7b QWen2 LLM
- Web ui access link http://alpha-one.local:8000/
- Direct download from PINE64 file server
- MD5 (GZip file): d62eeb1645c7b496a0815c4590f798c7
- File Size: 18.10GB
Default credentials | |
---|---|
Super user | eswin/eswin
|
This is the early test build that contains both 7b Deepseek and QWen2 LLM build, OS based on ROCKOS.
DD image for 32GB eMMC module and above
- for larger than 32GB eMMC, please use gpart to extend the file partition.
- Direct download from PINE64 file server
- MD5 (GZip file): 6669a436104e97e2ad90679e06f62d78
- File Size: 18.21GB
Default credentials | |
---|---|
Super user | eswin/eswin
|
To explore LLM, use terminal program and execute below command lines:
deepseek 7bLLM command line: sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/deepseek_r1_distill_qwen_7b/config.json
qwen2 7bLLM command line: sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_7b/config.json
qwen2 0.5bLLM command line: sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_0_5b/config.json
SDK releases
- SDK document (some in Chinese): https://files.pine64.org/SDK/StarPro64/docs.7z
- MD5 (7Zip file): 8ee9b660c336d9979191d212e9826226
- File Size: 34MB
- SDK Release:
- 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250228.7z
- MD5 (7Zip file): f9171ec8b30e5d4d8eda1185f72af5e4
- File Size: 1.932GB
- 20250330: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250330.7z
- MD5 (7Zip file): 8ddc861755ed26785e67674aad8db87c
- File Size: 1.946GB
- LLM and tools release:
- LLM 20250228: https://files.pine64.org/SDK/StarPro64/deepseek&qwen-v0228.7z
- MD5 (7Zip file): b8ee72ee6a8912afefac3fa43a18be87
- File Size: 722MB
- Tools 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_nn-tools_Release_20250228.7z
- MD5 (7Zip file): 868434b274412e173c3e264118dcb336
- File Size: 6.625GB
Main Board and SoC Specification
- Based on StarPro64 Single Board Computer wiki page
- Based on ESWIN EIC7700X SoC
Features
System Memory
- 32GB 64bits LPDDR5@6400MHz RAM Memory.
- 64GB eMMC preintsalled with 7b Deepseek/Qwen LLM
Case
- CNC from single Aluminum block
- Passive cooling, built-in heat pipe that directly contact with SoC
Network
- Dual 10/100/1000Mbps Ethernet
- 2.4GHz/5GHz MIMO WiFi 802.11 b/g/n/ac/ax with Bluetooth 5.3
Expansion Ports
- 2× USB3.0 Dedicated Host port
- 2× USB2.0 Shared Host port
- Digital Video output up to 4K@60Hz
- 3.5mm audio Jack with mic in
Certifications
- Not yet available
Potential Improvement
- Current 7bLLM throughput is around 3.5 tokens/second using docker form, potential improve upto 10 tokens/second when operates LLM in native mode.
- Potential increase LLM capability from 7b to 15b with system software optimization
- If ALPHA-One proven its potential, consider release ALPHA-Two which can host up to 30b LLM