Audience: Everyone

Hardware Compatibility Matrix

This document provides a comprehensive list of supported GPU hardware and their corresponding compute stacks within the NeuralDrive environment.

Supported Graphics Hardware

VendorFamilyExample CardsCompute StackDriverStatus
NVIDIATuringRTX 2060-2080, T4CUDA 12.x535+Supported
NVIDIAAmpereRTX 3060-3090, A100, A2000CUDA 12.x535+Supported
NVIDIAAda LovelaceRTX 4060-4090, L40CUDA 12.x535+Supported
NVIDIAHopperH100CUDA 12.x535+Supported
AMDRDNA 3RX 7600-7900 XTXROCm 6.xamdgpuSupported
AMDCDNA 2/3MI250, MI300ROCm 6.xamdgpuSupported
IntelArc AlchemistA770, A750oneAPI/SYCLi915Experimental
CPU-onlyAny x86_64AnyN/AN/ASupported (slow)

VRAM Recommendations

The table below outlines the minimum VRAM requirements for common model sizes at various quantization levels.

Model SizeQuantization (Q4_K_M)Quantization (Q8_0)Full Weights (FP16)
7B - 8B6 GB10 GB16 GB
13B - 14B10 GB16 GB32 GB
30B - 34B24 GB40 GB64 GB
70B48 GB80 GB140 GB

Note: These values are estimates and do not include the memory required for context window overhead (KV cache). High context lengths will increase VRAM consumption.

Important Hardware Considerations

  • Secure Boot: NVIDIA drivers require MOK (Machine Owner Key) enrollment or Secure Boot to be disabled. NeuralDrive uses DKMS-based driver installation.
  • Bus Interface: PCIe 4.0 or 5.0 is recommended to minimize latency during model loading and context ingestion.
  • Power Supply: Ensure your power supply (PSU) is rated for the peak power consumption of your GPU(s) during inference.
  • Cooling: GPUs can generate significant heat during long-running inference tasks. Ensure your system has adequate thermal management.

Note: For detailed hardware setup instructions, see Hardware Requirements. If your GPU is not detected, consult the GPU Troubleshooting guide.