Hala Apex (STHT1)
Desktop GPU Power,
Mini PC Footprint
The Hala Apex pairs a discrete AMD Radeon RX 7600 XT with 16 GB of GDDR6 VRAM alongside an AMD Hawk Point 8845HS CPU, triple-fan cooling, and an internal 336W ATX power supply — all in a compact metal chassis. Real GPU firepower for AI inference, gaming, and creative workloads without an external power brick.
A Real GPU In A Mini PC
Discrete RX 7600 XT graphics, triple-fan cooling, and an internal PSU — no compromises, no power bricks.
Discrete RX 7600 XT GPU
A full AMD Radeon RX 7600 XT with 16 GB GDDR6 VRAM inside a mini PC. Run local AI inference, game at high settings, or accelerate creative workloads with dedicated GPU compute.
Internal 336W ATX PSU
No external power brick. A built-in 336W ATX power supply (12V/28A) with a standard IEC inlet delivers clean, stable power for sustained peak GPU + CPU loads.
Triple-Fan Cooling
Dedicated CPU, GPU, and system fans with a full mesh side panel ensure the RX 7600 XT and Hawk Point CPU run cool under sustained workloads — no thermal throttling.
8K HDMI 2.1 + DP 1.4b
HDMI 2.1 FRL output supports up to 8K@60Hz. Pair it with DisplayPort 1.4b and USB-C DP alt mode for multi-monitor setups across gaming, trading, or command centers.
80 TOPS NPU. 32CU GPU.
Infinite Sovereignty.
The Hala Apex features the AMD Strix Halo AI 385, delivering 80 TOPS of NPU performance and 32 Compute Units of RDNA 3.5 graphics. This is the ultimate compact workstation for local AI development, training, and high-fidelity inference.
🧠Strix Halo AI 385
- 80 TOPS NPU for extreme AI workloads
- AMD Strix Halo AI 385 — 12-core Zen 5 architecture
- 32CU RDNA 3.5 graphics — high-performance integrated GPU
⚡Professional AI Engineering
- LPDDR5 Memory — 128GB high-bandwidth support
- 2× M.2 2280 PCIe 5.0×4 NVMe SSD
- WiFi 7 + 2.5G LAN + BT 5.4
🔌Internal Power & Cooling
- 336W ATX PSU (12V/28A) — standard IEC inlet
- Triple-fan system: CPU + GPU + System fan
- Full mesh side panel for unrestricted airflow
Hala Apex vs. Performance Leaders
Why settle for cloud-taxed, proprietary hardware when you can own your data and your compute? Hala delivers industrial-grade local AI at a fraction of the workstation cost.
| Feature | Hala Apex | Mac Mini (M4 Pro) | Dell Precision 3260 |
|---|---|---|---|
| AI Performance (NPU) | 80 TOPS | 38 TOPS | 11 TOPS |
| Max Memory | 128GB Support | 64GB Unified | 64GB DDR5 |
| GPU Cores | 32CU RDNA 3.5 | 20-Core GPU | RTX 2000 Ada (SFF) |
| Privacy / Stack | 100% Zero-Cloud | Apple Intelligence | Windows / Cloud-First |
| Starting Price | $1,699 | $1,999+ | $1,400+ |
Endless Possibilities With The Hala Apex
GPU-Accelerated AI Inference
16 GB of dedicated VRAM handles large model weights that integrated GPUs cannot. Run Stable Diffusion, LLM inference, and computer vision locally.
Compact Gaming Rig
The RX 7600 XT delivers AAA gaming at 1080p and 1440p. AMD Smart Shift RSR dynamically balances power between CPU and GPU for peak FPS.
Multi-Display Workstation
8K@60Hz HDMI 2.1, DisplayPort 1.4b, and USB-C DP alt mode drive up to three displays for trading desks, design studios, and dev setups.
Edge Compute Node
2.5G LAN, WiFi 6, and a discrete GPU turn the Hala Apex into a high-performance edge gateway for real-time analytics and model serving.
One Machine. Every
Workload.
From AI inference to AAA gaming to enterprise fleet deployment, the XB35 adapts. A discrete RX 7600 XT GPU and AMD Advantage technology handle compute-heavy tasks, while an internal ATX PSU and optional TPM keep things clean and compliant — all in a compact, triple-fan cooled chassis.
Local AI & GPU Inference
16 GB of dedicated GDDR6 VRAM runs models that APU-based mini PCs simply cannot. Accelerate Stable Diffusion, LLM inference, and ONNX workloads natively.
- Stable Diffusion / SDXL
- LLM Inference (GGUF)
- ONNX / TensorRT
Gaming & Content Creation
The RX 7600 XT with AMD Smart Shift RSR delivers AAA gaming at 1080p–1440p, and accelerates DaVinci Resolve, Blender, and real-time 3D workflows.
- AAA Gaming @ 1440p
- Video Editing
- 3D Rendering
Multi-Display Productivity
Drive up to three screens via HDMI 2.1 (8K@60Hz), DisplayPort 1.4b, and USB-C DP alt mode — ideal for trading, dev, and design workflows.
- Trading Desks
- Developer Setups
- Design Studios
Enterprise & Edge Deployment
Internal ATX PSU, optional TPM (SLB9670VQ2), Modern Standby, and Pluton security make fleet deployment and compliance straightforward.
- Fleet Management
- TPM / Pluton Security
- Edge Inference Nodes
Key Specifications
Discrete GPU + dedicated CPU in a triple-fan cooled mini chassis
Integrated GPU
32CU RDNA 3.5
AMD Radeon™ RDNA 3.5 graphics with 32 Compute Units. Massive parallel processing power for AI inference and professional visualization workflows.
Compatibility: Supports: Stable Diffusion, ONNX, ROCm, DaVinci Resolve, Blender, Unreal Engine, and high-performance local LLM inference.
AI Power
80 TOPS
NPU Acceleration
CPU
AI 385
Strix Halo · 12-core
System RAM
LPDDR5
128GB Support
Video Out
HDMI 2.1
8K@60Hz + DP 1.4b
Networking
WiFi 7
2.5G LAN · BT 5.4
Power
Internal
Integrated PSU
Cooling
Triple Fan
Dynamic Airflow
Storage
2× NVMe
M.2 2280 PCIe 5.0
Ready To Deploy The Hala Apex?
Check More Products
Discover other amazing products to help drive local AI efficiencies in your organization.
Hala Nexus(STHT1)
Coming Soon
Flagship 16-core AI workstation with 80 TOPS NPU and 128GB LPDDR5.
Hala Pulse(STHT1)
Coming Soon
Ultra-compact 127mm AI workstation with 16-core Strix Halo AI 395 and 80 TOPS NPU.
Hala Core(STHT1)
Coming Soon
Entry-level AI node with 8-core Ryzen 7840, 16 TOPS NPU, and 32GB RAM.
Motherboard STH-1
Coming Soon
Thin Mini-ITX Strix Halo motherboard with 64GB LPDDR5X, 1× PCIe 4.0 x4 + 1× PCIe 3.0 x4, and dual HDMI 2.1.
Motherboard STH-T1-8
Coming Soon
8-core Strix Halo motherboard configuration with 128GB LPDDR5X, dual M.2 PCIe 4.0 x4, and 19V DC-in.