TinkerLab
ARTIFACT // RUN-EVOX5-UNSLOTH-NPU-NEMOTRON35.SH (SH)

GMKtec EVO-X5 Pro (192GB / 160GB UMA) + Unsloth XDNA 2 NPU (Q4NX) & NVIDIA Nemotron 3.5 Super VL 120B Runner (run-evox5-unsloth-npu-nemotron35.sh)

Audits 160GB Radeon 8065S UMA & /dev/accel/accel0 XDNA 2 NPU on GMKtec EVO-X5 Pro (Ryzen AI Max+ PRO 495), runs NVIDIA Nemotron-3.5-Super-VL-120B-A12B or Lightning 30B with configurable reasoning budgets, and pairs Unsloth Desktop Lemonade/FastFlowLM Q4NX NPU inference.

[KEY VERIFIED TAKEAWAY / TL;DR]This reproducible configuration artifact "GMKtec EVO-X5 Pro (192GB / 160GB UMA) + Unsloth XDNA 2 NPU (Q4NX) & NVIDIA Nemotron 3.5 Super VL 120B Runner" (run-evox5-unsloth-npu-nemotron35.sh, SH) is paired with Tinker AI Lab's hardware-verified guide "gmktec-evo-x5-pro-192gb-unsloth-desktop-xdna2-npu-and-nemotron-35-super-vl-120b". It exposes 5 customizable browser variables (EXEC_MODE=evox5_nemotron35_super_vl, NEMOTRON_GGUF=./models/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Q4_K_M.gguf, NPU_Q4NX_MODEL=Qwen3.6-35B-A3B-NPU2, CTX_LEN=65536, IGPU_PORT=8080) with loopback-first security defaults.
01 // HOMELABLocal AI / HomeLab· Verified: 2026-11-20
Browse All 60 Artifacts →
run-evox5-unsloth-npu-nemotron35.sh

GMKtec EVO-X5 Pro (192GB / 160GB UMA) + Unsloth XDNA 2 NPU (Q4NX) & NVIDIA Nemotron 3.5 Super VL 120B Runner

Audits 160GB Radeon 8065S UMA & /dev/accel/accel0 XDNA 2 NPU on GMKtec EVO-X5 Pro (Ryzen AI Max+ PRO 495), runs NVIDIA Nemotron-3.5-Super-VL-120B-A12B or Lightning 30B with configurable reasoning budgets, and pairs Unsloth Desktop Lemonade/FastFlowLM Q4NX NPU inference.

View Paired Guide →
Customizable Variables (Saved in Browser)
UTF-8 Encoded · Live Client-Side Compilation
#!/usr/bin/env bash
# Tinker AI — GMKtec EVO-X5 Pro (192GB / 160GB VRAM) + Unsloth XDNA 2 NPU (Q4NX) & Nemotron 3.5 Super VL 120B (Guide #60)
set -euo pipefail

MODE="evox5_nemotron35_super_vl"
GGUF="./models/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Q4_K_M.gguf"
NPU_MODEL="Qwen3.6-35B-A3B-NPU2"
CTX="65536"
PORT="8080"
NPU_PORT="$((PORT + 1))"

echo "=== [EVO-X5 Pro Audit] Checking 192GB UMA, Linux 7.4 iommu_perfopt & XDNA 2 NPU ==="
free -h
cat /sys/module/amdgpu/parameters/iommu_perfopt 2>/dev/null || echo "[TIP] Upgrade to Linux 7.4+ or add iommu=pt for +18-23% UMA tok/s"
ls -l /dev/accel/accel* 2>/dev/null || echo "[WARN] /dev/accel/accel0 not found; verify amdxdna driver for XDNA 2 NPU"

if [ "$MODE" = "evox5_nemotron35_super_vl" ]; then
  echo "=== [Radeon 8065S 160GB UMA] Serving Nemotron 3.5 Super VL 120B-A12B (Mamba-2 Hybrid, ctx=$CTX) ==="
  exec llama-server \
    -m "$GGUF" -ngl 99 -fa on \
    --cache-type-k q8_0 --cache-type-v q8_0 \
    -c "$CTX" --host 127.0.0.1 --port "$PORT"
elif [ "$MODE" = "unsloth_xdna2_npu_q4nx" ]; then
  echo "=== [Unsloth Desktop / Lemonade + FastFlowLM] Serving $NPU_MODEL (Q4NX) on 55 TOPS XDNA 2 NPU ==="
  exec lemonade-server serve \
    --backend flm \
    --model "$NPU_MODEL" \
    --host 127.0.0.1 --port "$NPU_PORT"
elif [ "$MODE" = "dual_igpu_npu_agent" ]; then
  echo "=== [Dual-Engine Concurrent Mode] iGPU ($PORT: Nemotron 3.5 VL) + XDNA 2 NPU ($NPU_PORT: $NPU_MODEL Q4NX) ==="
  lemonade-server serve --backend flm --model "$NPU_MODEL" --host 127.0.0.1 --port "$NPU_PORT" &
  exec llama-server \
    -m "$GGUF" -ngl 99 -fa on \
    --cache-type-k q8_0 --cache-type-v q8_0 \
    -c "$CTX" --host 127.0.0.1 --port "$PORT"
else
  echo "Unknown EXEC_MODE=$MODE (expected: evox5_nemotron35_super_vl | unsloth_xdna2_npu_q4nx | dual_igpu_npu_agent)" >&2
  exit 1
fi
PARAMETER SPECIFICATION // 参数化变量规范说明表

Customizable Parameter Reference for run-evox5-unsloth-npu-nemotron35.sh

This SH artifact exposes 5 template variables compiled client-side in your browser.

Template TokenParameter DescriptionVerified DefaultExample Format
{{EXEC_MODE}}Execution Mode (evox5_nemotron35_super_vl | unsloth_xdna2_npu_q4nx | dual_igpu_npu_agent)evox5_nemotron35_super_vlevox5_nemotron35_super_vl
{{NEMOTRON_GGUF}}Nemotron 3.5 GGUF Model Path./models/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Q4_K_M.gguf./models/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Q4_K_M.gguf
{{NPU_Q4NX_MODEL}}Unsloth XDNA 2 NPU Q4NX Model TagQwen3.6-35B-A3B-NPU2Qwen3.6-35B-A3B-NPU2
{{CTX_LEN}}Context Window (Mamba-2 Hybrid Low KV)6553665536
{{IGPU_PORT}}iGPU LLM API Port (NPU uses Port + 1)80808080
PAIRED HARDWARE MANIFEST // 配套实测环境与边界记录

Verified Environment for "192GB Desktop AI Workstation, Native XDNA 2 NPU & Mamba-2 Hybrid MoE: GMKtec EVO-X5 Pro (Ryzen AI Max+ PRO 495 · 160GB VRAM) + Unsloth Desktop Q4NX NPU Running NVIDIA Nemotron 3.5 Super VL (120B-A12B) & Lightning 30B"

Tested Hardware & OS

GMKtec EVO-X5 Pro (AMD Ryzen AI Max+ PRO 495 · Radeon 8065S 40 CU · 192GB LPDDR5X-8533 / 273 GB/s / 160GB VRAM · 55 TOPS XDNA 2 NPU · Dual 10GbE)

Pinned Stack & Model Versions
Unsloth Desktop (Nov 2026 · AMD Lemonade SDK + FastFlowLM Q4NX NPU)llama.cpp v1.0.0+ / ROCm 7.2+ / Linux 7.4+ (amdgpu.iommu_perfopt=1)nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4 / GGUF · OpenMDW-1.1)nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B & Qwen3.6-35B-A3B-NPU2 (Q4NX)
Offline Boundary (100% Local Desktop Multimodal Reasoning + NPU Agent Execution)

Nemotron 3.5 weights (OpenMDW-1.1) and Unsloth Desktop Q4NX conversions run entirely on local CPU/iGPU/NPU; once downloaded, bind endpoints to 127.0.0.1 for zero outbound telemetry.

Known Operational Limits & Failure Modes
  • Unsloth Desktop XDNA 2 NPU inference requires models in the specialized Q4NX binary format (converted locally from GGUF on CPU via Unsloth’s Export utility) and runs through Lemonade + FastFlowLM—standard raw GGUF files cannot execute directly on /dev/accel/accel0 without Q4NX conversion.
  • Nemotron-3.5-Super-VL-120B-A12B supports 2-minute MP4 video and RGB images via its C-RADIO v4-H vision encoder, plus 1M context via Mamba-2 state-space layers—verify your llama.cpp / vLLM build includes both the Mamba-2 hybrid cache and C-RADIO mmproj projector before feeding multimodal inputs.
  • While GMKtec EVO-X5 Pro allows up to 160GB VRAM allocation from its 192GB LPDDR5X-8533 pool, leaving <32GB for Linux/Windows OS + NPU Q4NX host buffers triggers swap stutter; cap iGPU model + KV budgets at <=135–145GB when running dual iGPU + NPU engines concurrently.
DEPLOYMENT CHECKLIST // 配置落地核验步骤

3-Step Verification Checklist After Deploying run-evox5-unsloth-npu-nemotron35.sh

  1. Raised UMA/GTT allocation on GMKtec EVO-X5 Pro (192GB) while reserving >=32–40 GB for OS + NPU Q4NX host buffers so concurrent iGPU + NPU workloads never trigger SSD swap.
  2. Converted or pulled a Q4NX model inside Unsloth Desktop (Lemonade + FastFlowLM) and confirmed http://127.0.0.1:8081/v1/chat/completions executes on /dev/accel/accel0 without spiking GPU utilization.
  3. Verified enable_thinking=False (fast mode) vs enable_thinking=True (deep reasoning) on Nemotron-3.5-Super-VL-120B-A12B and confirmed C-RADIO mmproj compatibility before running image/video prompts.