Edge AI Runner: Pi 5 + DEEPX DX-M1M (3W), Jetson Orin Nano 2 (15W) & RISC-V RVA23 (LFM3-1.7B) (run-edge-orin-nano2-deepx-riscv.sh)
Audits edge NPU/GPU/RISC-V RVV devices and launches Liquid AI LFM3-1.7B (llama.cpp v1.0.0) alongside DEEPX DX-M1M 3W vision pipelines or Jetson CUDA acceleration.
Edge AI Runner: Pi 5 + DEEPX DX-M1M (3W), Jetson Orin Nano 2 (15W) & RISC-V RVA23 (LFM3-1.7B)
Audits edge NPU/GPU/RISC-V RVV devices and launches Liquid AI LFM3-1.7B (llama.cpp v1.0.0) alongside DEEPX DX-M1M 3W vision pipelines or Jetson CUDA acceleration.
#!/usr/bin/env bash
# Tinker AI — Edge AI Runner: DEEPX DX-M1M (3W Pi 5) / Jetson Orin Nano 2 / RISC-V RVA23 (Guide #52)
set -euo pipefail
PLATFORM="pi5_deepx_lfm3"
MODEL="models/LFM3-1.7B-Q4_K_M.gguf"
THREADS="4"
PORT="8080"
if [ "$PLATFORM" = "pi5_deepx_lfm3" ]; then
echo "=== [Pi 5 + DEEPX DX-M1M 3W Mode] Checking PCIe Gen3 NPU & launching LFM3-1.7B on CPU ==="
lspci | grep -iE "DEEPX|DX-M1" || echo "Note: DEEPX M.2 NPU not detected on PCIe; running CPU-only LFM3."
exec llama-server -m "$MODEL" -t "$THREADS" -c 16384 -fa on --cache-type-k q8_0 --port "$PORT"
elif [ "$PLATFORM" = "jetson_cuda" ]; then
echo "=== [Jetson Orin Nano 2 / Orin Nano Super CUDA Mode] Offloading 100% layers to GPU ==="
nvpmodel -q || true
exec llama-server -m "$MODEL" -ngl 99 -c 32768 -fa on --cache-type-k fp8_e4m3 --port "$PORT"
elif [ "$PLATFORM" = "riscv_rvv" ]; then
echo "=== [RISC-V RVA23 Vector Mode] Checking RVV ISA & running llama.cpp v1.0.0 ==="
grep -i "isa" /proc/cpuinfo | head -n 2 || true
exec llama-server -m "$MODEL" -t "$THREADS" -c 16384 --port "$PORT"
else
echo "Unknown EDGE_PLATFORM=$PLATFORM (expected: pi5_deepx_lfm3 | jetson_cuda | riscv_rvv)" >&2
exit 1
fi
Customizable Parameter Reference for run-edge-orin-nano2-deepx-riscv.sh
This SH artifact exposes 4 template variables compiled client-side in your browser.
| Template Token | Parameter Description | Verified Default | Example Format |
|---|---|---|---|
{{EDGE_PLATFORM}} | Target Edge Platform (pi5_deepx_lfm3 | jetson_cuda | riscv_rvv) | pi5_deepx_lfm3 | pi5_deepx_lfm3 |
{{LFM3_GGUF_PATH}} | LFM3-1.7B / LFM3-VL-2B GGUF Path | models/LFM3-1.7B-Q4_K_M.gguf | models/LFM3-1.7B-Q4_K_M.gguf |
{{CPU_THREADS}} | Physical CPU Threads (-t) | 4 | 4 |
{{SERVER_PORT}} | OpenAI API Port | 8080 | 8080 |
Verified Environment for "2026–2027 Edge AI Hardware Guide: NVIDIA Jetson Orin Nano 2 (78 TOPS · 15W) vs Raspberry Pi 5 + DEEPX DX-M1M (3W · 25 TOPS) vs RISC-V RVA23 (SpacemiT V100 / XuanTie C950)"
Edge Targets: NVIDIA Jetson Orin Nano 2 (78 TOPS · 8GB LPDDR5x · 15W, announced Aug 2026 for H1 2027), Raspberry Pi 5 (8GB) + Sixfab AI HAT+ (DEEPX DX-M1M 25 TOPS · ~3W NPU · 13–15W total system), RISC-V RVA23 Host (SpacemiT V100 / XuanTie C950)
~3W NPU, 13–15W total Pi 5 draw)llama.cpp v1.0.0 (LiquidAI/LFM3-1.7B Q4_K_M ~1.05 GB, RVV / ARM NEON / CUDA)Jetson Orin Nano 2 reference specs (78 TOPS, 8GB LPDDR5x, 8-core Arm CPU, 15W envelope)All vision detection, NPU inference, and local LFM3-1.7B text/tool-calling run completely offline on a 15W–27W DC/USB-C power budget.
DEEPX DX-M1M(1–2 GB Onboard LPDDR4x) Is a Vision/Encoder NPU—Pair It With Host CPU for LLMs: At~3Wand~$30,DX-M1M(25 TOPS INT8) excels at multi-stream YOLO/vision workloads, but its 1–2 GB onboard DRAM cannot hold a 7B LLM. On Pi 5, offload cameras/YOLO toDX-M1Mand runLFM3-1.7BorBitNet-b1.58-2B-4Ton the Pi 5 CPU.- Jetson Orin Nano 2 Availability Window (H1 2027) & 8GB Ceiling: Announced August 25, 2026, Orin Nano 2 developer kits ship in H1 2027 (pricing pending). Its 8 GB LPDDR5x remains tight for 7B–8B LLMs with large KV caches—size workloads for
1.7B–4Bmodels or use Orin Nano Super today. - RISC-V RVA23 Software Maturity: While
RVA23standardizes RISC-V Vector (RVV 1.0) extensions forllama.cpp, discrete GPU/NPU driver support on RISC-V PCIe 5.0 hosts still lags x86/ARM64—verify kernel/SDK compatibility before buying.
3-Step Verification Checklist After Deploying run-edge-orin-nano2-deepx-riscv.sh
- Verified 27W USB-C PD power supply (5V/5A) and enabled
dtparam=pciex1_gen=3on Raspberry Pi 5 before loading M.2 NPU HATs. - Separated vision workloads (
DEEPX DX-M1M1–2 GB onboard RAM) from host SLM inference (LFM3-1.7B~1.05 GB in host RAM). - Monitored
vcgencmd measure_temp/tegrastatsunder sustained 15W load to confirm zero thermal throttling.