Framework Desktop (Ryzen AI Max+ 395 128GB)
4.5-liter modular Mini-ITX workstation powered by AMD's 16-core Ryzen AI Max+ 395 ('Strix Halo') APU with a 40-CU Radeon 8060S GPU and 128GB unified LPDDR5X-8000 memory for local 70B–120B LLM execution.
Key Engineering Highlights
- Allocates up to 112GB of its 128GB LPDDR5X-8000 unified pool directly to the 40-CU Radeon 8060S GPU under Linux ROCm (`gfx1151`)
- Runs 70B Q4_K_M models at 14.8 tokens/sec and 100B+ Mixture-of-Experts (MoE) models at 38 tokens/sec for under $2,000
- Standard Mini-ITX motherboard with Noctua 120mm fan stays whisper-quiet (<28 dBA) under continuous 140W LLM inference
Full Hardware Specifications
| Processor / Edge SoC | AMD Ryzen AI Max+ 395 (16C Zen 5 + 40-CU RDNA 3.5 + 50 TOPS XDNA 2) |
|---|---|
| AI Model Stack | Llama-4-70B / Qwen3-72B / DeepSeek MoE via ROCm 6.4 & llama.cpp |
| Display & Optics | Dual USB4 DisplayPort 2.1 + Dual HDMI 2.1 |
| Camera & Vision | None (Headless or Workstation Node) |
| Measured Weight | 3.1kg (4.5L Modular Mini-ITX Chassis w/ Noctua Cooling) |
| Battery & Runtime | Internal 400W 80+ Platinum Flex-ATX PSU (120W–140W Sustained APU TDP) |
| Connectivity & I/O | 5GbE Ethernet + Wi-Fi 7 + 2× Front Modular Expansion Card Slots |
| Sensors & Acoustics | Configurable UMA Allocation (Up to 112GB Dedicated iGPU VRAM in BIOS) |
⚖️ Side-by-Side Comparison: Framework Desktop (Ryzen AI Max+ 395 128GB) vs. Edge Compute & DevKits Peers
Direct specification comparison against leading competing devices in the Edge Compute & DevKits category.
| Specification | Framework Desktop (Ryzen AI Max+ 395 128GB) (Current) | NVIDIA Jetson Orin NX Super Edge AI DevKit → | Xiaozhi AI Voice Cube Pro (ESP32-S3 Open DevKit) → | Apple Mac mini (M5 Pro 64GB) Private AI Node → |
|---|---|---|---|---|
| Brand | Framework × AMD | NVIDIA | Open Hardware Community | Apple |
| Retail Price | $1,999 | $499 | $12 | $1,799 |
| Lab Rating | ||||
| Edge SoC | AMD Ryzen AI Max+ 395 (16C Zen 5 + 40-CU RDNA 3.5 + 50 TOPS XDNA 2) | NVIDIA Ampere GPU (1024 CUDA + 32 Tensor Cores) | Espressif ESP32-S3R8 (Dual-Core LX7 @ 240MHz + 8MB PSRAM) | Apple M5 Pro (14c CPU + 20c GPU + 16c Neural Engine) |
| AI Model Stack | Llama-4-70B / Qwen3-72B / DeepSeek MoE via ROCm 6.4 & llama.cpp | Runs Llama-3.2 8B / Qwen2.5-VL 7B / YOLO11 Locally | Edge ESP-SR Wake + Realtime Cloud Voice LLMs | MLX Accelerated Qwen3-32B / Llama-3.3-70B |
| Display / Optics | Dual USB4 DisplayPort 2.1 + Dual HDMI 2.1 | HDMI 2.1 / DP 1.4 (Up to 8K) | 1.28-inch Circular IPS LCD (240×240) / 0.96" OLED | Supports up to three 6K displays |
| Camera | None (Headless or Workstation Node) | Dual MIPI CSI-2 Camera Lanes + 4× USB 3.2 | Optional OV2640 / GC2145 Camera Module | External USB-C / Studio Display Camera |
| Weight | 3.1kg (4.5L Modular Mini-ITX Chassis w/ Noctua Cooling) | 450g (including active heatsink & carrier board) | 62g (with 3D-printed enclosure & speaker cavity) | 730g |
| Battery | Internal 400W 80+ Platinum Flex-ATX PSU (120W–140W Sustained APU TDP) | 19V DC Input (15W–40W configurable TDP) | 800mAh LiPo (5h continuous dialogue) | Internal 155W PSU (4W idle draw) |
📚 Related Engineering Teardowns & Reviews
Browse All 83 Articles →Framework Desktop (Ryzen AI Max+ 395 128GB) Local LLM Benchmark: AMD Strix Halo vs NVIDIA DGX Spark GB10 vs Mac mini M5 Pro
RECIWO Labs benchmarked the $1,999 4.5L Framework Desktop powered by AMD's 16-core Ryzen AI Max+ 395 ('Strix Halo') and 128GB unified LPDDR5X-8000 memory, comparing ROCm 6.4 token generation and prompt prefill speeds against the $2,999 NVIDIA DGX Spark (GB10) and $1,799 Apple Mac mini M5 Pro.
Meta Ray-Ban Display & sEMG Neural Band Teardown: Inside the 5,000-Nit Waveguide and Wrist Neuromotor Interface
RECIWO Labs disassembled the $799 Meta Ray-Ban Display and IPX7 sEMG Neural Band, benchmarking its 5,000-nit 42-PPD geometric waveguide, 69g thermal profile, and 14ms wrist neuromotor gesture latency against Xiaomi AI Glasses and Even Realities G2 Air.
Unitree R1 ($5,900) vs Unitree G1 ($16,000) Developer Benchmark: 25kg Agile Locomotion, Sim-to-Real RL, and Actuator Density
RECIWO Labs put the 25kg, $5,900 Unitree R1 ultralight humanoid head-to-head against the 35kg Unitree G1 EDU and Booster T1, evaluating Quasi-Direct Drive (QDD) joint torque-to-weight ratios, Isaac Lab sim-to-real transfer, and manipulation payload limits.
Micro-Form-Factor AI Voice Hardware Shootout: 9.9g Anker Soundcore Work vs 3.8g Vocci AI Ring vs PLAUD NotePin Pro
RECIWO Labs tested the three leading ambient AI memory form factors of late 2026—the 9.9g Anker Soundcore Work coin, the 3.8g Gyges Labs Vocci MCP Ring, and the 22g PLAUD NotePin Pro—measuring far-field WER, collar fabric sag, and automated MCP agent execution.
