BBrainOutput
AMD·GPU

AMD Radeon RX 7800 XT 16GB: Specs & Local-AI Compatibility

16GB RDNA 3 gpu. Indexed entry — detailed specs (bandwidth, TFLOPS, power) to verify.

Indexed from vendor-catalog and approved for the catalog. Figures are sourced/derived (confidence: approximate); editorial review of strengths and use cases is pending.

Specs

Memory
16 GB
Memory type
to verify
Bandwidth
to verify
Approx FP16
to verify
Architecture
RDNA 3
Process
to verify
Power
to verify
Launch
2023

Models this chip can run

Open models graded for a single AMD Radeon RX 7800 XT 16GB, best fit first.

  • DeepSeek-Coder V2 (class)
    DeepSeek · ~16B · 128K ctx · DeepSeek License

    Fits at Q4_K_M (~11GB) with ~3.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~11GBRuns well
  • StarCoder2 15B
    StarCoder · ~15B · 16K ctx · BigCode OpenRAIL-M

    Fits at Q4_K_M (~10GB) with ~4.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~10GBRuns well
  • Qwen2.5 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at Q4_K_M (~10GB) with ~4.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~10GBRuns well
  • Qwen3 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at Q4_K_M (~10GB) with ~4.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~10GBRuns well
  • Phi-3 Medium (14B)
    Phi · ~14B · 128K ctx · MIT

    Fits at Q4_K_M (~9GB) with ~5.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~9GBRuns well
  • Phi-4 (14B)
    Phi · ~14B · 16K ctx · MIT

    Fits at Q4_K_M (~9GB) with ~5.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~9GBRuns well
  • DeepSeek-R1 Distill 14B
    DeepSeek · ~14B · 128K ctx · MIT

    Fits at Q4_K_M (~10GB) with ~4.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~10GBRuns well
  • Qwen2.5-Coder 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at Q4_K_M (~10GB) with ~4.1GB headroom — about 1 concurrent instance.

    Q4_K_M · ~10GBRuns well

Build a private AI Business OS on AMD Radeon RX 7800 XT 16GB

Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.

Explore the AI Business OS