Workspace / Compute overview
Connect wallet ↗
YOUR WALLET. YOUR HARDWARE.

Your edge. Supercharged.

Connect with Solana. Create with a real NVIDIA GPU.

Connecting to Convex
SolanaWALLET ACCESS

Intelligence.
In your hands.

Sign in with Solana. Run on NVIDIA Jetson Orin.
Real CUDA inference, from your own edge.

512 CUDA cores4 GB shared memorySM 8.7
Checking inference gateway…Wallet authenticated · CUDA accelerated
NVIDIA
HARDWARE INSIDE

NVIDIA Jetson Orin Nano

CLAWD runs inference on an NVIDIA GPU.
Independent project; no NVIDIA sponsorship or endorsement.

NVIDIA hardware, live

Waiting for device sample
GPU UTILIZATION
Measured GPU activity
GPU CLOCK
Dynamic frequency · MHz
SHARED MEMORY
CPU + GPU unified RAM
GPU TEMPERATURE
Live thermal sensor

CUDA activity

Measured on the Orin · sampled every 5 seconds

LAST 10 MIN
100%50%0%
Waiting for live telemetry

Inference performance

Q4_K_M
tokens / second

Last completed generation · llama.cpp

Request latency
GPU slot
Checking
Requests / failures¹
FP32 capacity estimate²
CPU UTILIZATION
NODE UPTIME
FREE DISK
SWAP USED
BOARD POWERUnavailable
DATA BACKENDConvex

¹ Since request tracking was enabled. ² Calculated FP32 ceiling at the current GPU clock (512 cores × 2 × GHz); not measured TFLOPS or Tensor Core TOPS. Board power is unavailable without sensor read permission.

Put your GPU to work

OpenAI-compatible · Streaming responses

Playground CLAWD

Qwen 2.5 · 0.5B

What will you build?

Ask a question and watch your GPU respond.

Runs on your Orin GPU

Your Solana access

Solana

Your wallet. Your compute.

Connect any Solana wallet with message signing. No token balance required.

Connect a wallet to unlock inference.

12 requests / minute per wallet1 shared inference slot2,048 token context · 1,024 output capKeys expire after 30 days
01 / CONNECT

Sign with Solana

Prove wallet ownership with a message. Receive your own revocable API key.

02 / ACCELERATENVIDIA Jetson Orin

Run on your GPU

Qwen inference on 512 CUDA cores. Stream every response from real hardware.

03 / OBSERVE

See every pulse

Convex streams GPU telemetry to your dashboard, straight from the device.

BUILT FOR DEVELOPERS

Your next API call runs here.

BASE URL https://clawd-orin-8bit.fly.dev/v1