nexa-sdk
nexa-sdk copied to clipboard
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Suppo...
[nexa-cli_macos_arm64.pkg] nexa infer NexaAI/Qwen3-1.7B-4bit-MLX ERROR:root:Model type qwen3 not supported. โ ๏ธ Oops. Model failed to load. ๐ Try these: - Verify your system meets the model's requirements. - Seek help in...
Running on Lenovo Legion Pro 7 16IAX10H. Intelยฎ AI Boost driver: 32.0.100.4404 (2025-10-29) Downloaded from github page: https://public-storage.nexa4ai.com/nexa_sdk/downloads/nexa-cli_windows_x86_64.exe Model from website: [NexaAI/deepSeek-r1-distill-qwen-7B-intel-npu](https://sdk.nexa.ai/model/DeepSeek-R1-Distill-Qwen-7B-Intel-NPU) Runnin with: nexa infer NexaAI/deepSeek-r1-distill-qwen-7B-intel-npu give me: nexa...
win10 x64, Intel Xeon E5-2680, NIVDIA GeForce RTX 2060 nexa list Nov 29 20:13:49.927 INF store\manager.go:74 Checking model directory name=NexaAI/DeepSeek-OCR.Q4_0 Nov 29 20:13:49.991 INF store\manager.go:74 Checking model directory name=NexaAI/DeepSeek-OCR.Q4_K Nov...
**Problem** Google Play requires 16KB page alignment for apps targeting Android 15+ (API 35) by Nov 1, 2025. Plugin is currently flagging a "Does not support 16 KB" error in...
Hi, Iโm seeing a license error when using the Android demo. - Repo: https://github.com/NexaAI/nexa-sdk/tree/main/bindings/android - Device: Xiaomi Pad 8 Pro - Android Gradle Plugin: 8.5.0 - Demo code: not modified...
Nexa serve is always doing the infer by cpu. I have tested with the deepseek ocr model. with infer in the cli, everything is fine, when calling it with nexa...
I am trying to deploy OmniNeural- 4B on Android smartphones with Qualcomm Snapdragon 8 Elite SoC such as Samsung S25 Ultra. I am following the instruction in Nexa Android SDK...