TinkerLab
ARTIFACT // RUN-KORA-SNAPDRAGON-X2-IQ10.SH (SH)

Snapdragon X2 Elite (Ascent QN10) & KORA OS FastRPC / Dragonwing IQ10 Heterogeneous Runner (run-kora-snapdragon-x2-iq10.sh)

Probes Linux FastRPC CDSP device nodes for Hexagon NPU offload, checks RAM ceiling (32GB Ascent QN10 vs 64GB Dragonwing IQ10), and launches llama-server with Q8_0 KV cache.

[KEY VERIFIED TAKEAWAY / TL;DR]This reproducible configuration artifact "Snapdragon X2 Elite (Ascent QN10) & KORA OS FastRPC / Dragonwing IQ10 Heterogeneous Runner" (run-kora-snapdragon-x2-iq10.sh, SH) is paired with Tinker AI Lab's hardware-verified guide "asus-ascent-qn10-snapdragon-x2-elite-kora-os-fastrpc-vs-qualcomm-dragonwing-iq10". It exposes 4 customizable browser variables (DEVICE_PROFILE=ascent_qn10_32g, MODEL_GGUF=./models/Qwen3.5-27B-Q4_K_M.gguf, CTX_LEN=16384, API_PORT=8080) with loopback-first security defaults.
01 // HOMELABLocal AI / HomeLab· Verified: 2026-11-17
Browse All 60 Artifacts →
run-kora-snapdragon-x2-iq10.sh

Snapdragon X2 Elite (Ascent QN10) & KORA OS FastRPC / Dragonwing IQ10 Heterogeneous Runner

Probes Linux FastRPC CDSP device nodes for Hexagon NPU offload, checks RAM ceiling (32GB Ascent QN10 vs 64GB Dragonwing IQ10), and launches llama-server with Q8_0 KV cache.

View Paired Guide →
Customizable Variables (Saved in Browser)
UTF-8 Encoded · Live Client-Side Compilation
#!/usr/bin/env bash
# Tinker AI — ASUS Ascent QN10 (Snapdragon X2 Elite) & Dragonwing IQ10 Runner (Guide #54)
set -euo pipefail

DEV="ascent_qn10_32g"
MODEL="./models/Qwen3.5-27B-Q4_K_M.gguf"
CTX="16384"
PORT="8080"

echo "=== [1/2] Probing Qualcomm FastRPC Hexagon NPU & Memory Ceiling ($DEV) ==="
ls -l /dev/fastrpc-* 2>/dev/null || echo "INFO: /dev/fastrpc-* not present; running on Oryon CPU + Adreno GPU."
free -h

echo "=== [2/2] Launching llama-server with Q8_0 KV Cache ==="
exec llama-server \
  -m "$MODEL" \
  -c "$CTX" -fa on \
  --cache-type-k q8_0 --cache-type-v q8_0 \
  --host 127.0.0.1 --port "$PORT"
PARAMETER SPECIFICATION // 参数化变量规范说明表

Customizable Parameter Reference for run-kora-snapdragon-x2-iq10.sh

This SH artifact exposes 4 template variables compiled client-side in your browser.

Template TokenParameter DescriptionVerified DefaultExample Format
{{DEVICE_PROFILE}}Target Device (ascent_qn10_32g | dragonwing_iq10_64g)ascent_qn10_32gascent_qn10_32g
{{MODEL_GGUF}}ARM64 GGUF Model Path./models/Qwen3.5-27B-Q4_K_M.gguf./models/Qwen3.5-27B-Q4_K_M.gguf
{{CTX_LEN}}Context Window (-c)1638416384
{{API_PORT}}Localhost API Port80808080
PAIRED HARDWARE MANIFEST // 配套实测环境与边界记录

Verified Environment for "ASUS Ascent QN10 (Snapdragon X2 Elite · 80 TOPS NPU) & KORA OS (NixOS + FastRPC CPU/GPU/NPU) vs Qualcomm Dragonwing IQ10 (700 TOPS · 64GB)"

Tested Hardware & OS

ASUS Ascent QN10 (Snapdragon X2E-88-100, 32GB LPDDR5x, 80 TOPS NPU) + KORA OS (NixOS) vs Qualcomm Dragonwing IQ10 (IQ-10800, 64GB LPDDR5x, 700 TOPS)

Pinned Stack & Model Versions
KORA OS (Cortex / Lemma)llama.cpp v1.0.0+Linux FastRPC / QNN SDKWindows 11 ARM64 / Ubuntu 26.04
Offline Boundary (100% Offline ARM64 Desktop & Industrial Edge AI)

ASUS Ascent QN10 uses non-upgradeable soldered 16GB/32GB LPDDR5x; always choose the 32GB SKU if running 14B–27B local models or concurrent NPU + GPU agent loops.

Known Operational Limits & Failure Modes
  • ASUS Ascent QN10 tops out at 32GB soldered LPDDR5x (8533–9600 MT/s), making 70B+ dense models impossible without LAN clustering; 16GB SKUs should be restricted to 7B–9B models.
  • Mainline Linux support for Snapdragon X2 Elite (including FastRPC Hexagon NPU offload used by KORA OS) requires recent upstream kernel patches and firmware blobs; Windows 11 Pro ARM64 remains the out-of-box default.
  • Qualcomm Dragonwing IQ10 targets industrial/AMR OEMs (SafeRTOS + Ubuntu/Linux) rather than consumer retail channels.
DEPLOYMENT CHECKLIST // 配置落地核验步骤

3-Step Verification Checklist After Deploying run-kora-snapdragon-x2-iq10.sh

  1. Selected the 32GB LPDDR5x Ascent QN10 SKU (soldered RAM cannot be upgraded later) and kept dual M.2 2280 NVMe airflow unobstructed.
  2. Verified /dev/fastrpc-cdsp and cdsprpcd status on KORA OS / Linux ARM64 before benchmarking Hexagon NPU offload.
  3. Matched model size to hardware tier (7B–27B Q4_K_M on 32GB Ascent QN10 vs 30B–70B / multi-stream robotics VLA on 64GB Dragonwing IQ10).