RigRoute LabsRigRoute ↗

← Hardware

System identity

AMD Radeon RX 7800 XT (16 GB dedicated VRAM)

Memory architecture

AMD Radeon RX 7800 XT — unknown

Dedicated VRAM: 16 GB, dedicated. llama.cpp's own Vulkan device query reported 15405 MiB free on this device at model-load time, on an adapter whose Vulkan properties report `uma: 0` -- a dedicated pool, not memory shared with system RAM.
Source: llama.cpp's own device-selection line in both accepted runs' raw stderr (`llama_prepare_model_devices: using device Vulkan0 (AMD Radeon RX 7800 XT) ... - 15405 MiB free`), published verbatim at /data. NOT from Windows WMI's Win32_VideoController.AdapterRAM, a 32-bit field that truncates for cards >=4GB -- which is why the structured result.json's hardware.accelerators[0].dedicatedVramBytes is honestly "UNKNOWN". Note this is free memory measured with a desktop session already resident, so it is a lower bound on the pool, not the pool's total; the accepted RX 9070 reported 15416 MiB free by the identical mechanism and the same llama.cpp build.
Reported device name: This card reports its real model name ("AMD Radeon RX 7800 XT") over Vulkan, unlike the accepted RX 9070, whose driver reports the generic "AMD Radeon(TM) Graphics".
Source: `ggml_vulkan: 0 = AMD Radeon RX 7800 XT (AMD proprietary driver)` in both accepted runs' raw stderr. Recorded because it shows the generic-string problem is a property of particular vendor drivers, not of a vendor or a generation -- which is why Labs' public identity comes from this registry rather than from rewriting driver strings.
Accepted benchmark runs
ModelContextPrompt processingGenerationAcceleration evidenceStatus
llama 8B Q4_08192763.53 tok/s74.81 tok/s33/33 layers offloaded to GPUPASS
qwen3 14B Q4_K - Medium8192417.30 tok/s43.51 tok/s41/41 layers offloaded to GPUPASS
Backend

Vulkan — target device: Vulkan

Methodology version

standard-ai-v0.1

Environment
Host OSMicrosoft Windows 11 Pro 10.0.26200
CPUAMD Ryzen 7 3700X 8-Core Processor
Installed memory32 GB
llama.cpp / llama-bench0.5.0-dev (build 11146, commit 7fe450e19)
Backends compiledCPU,RPC,Vulkan
Telemetry availability
PowerUNAVAILABLE
TemperatureUNAVAILABLE
Accelerator memoryUNAVAILABLE

Missing telemetry is shown as UNAVAILABLE, never estimated or substituted. Throughput measurements are unaffected by missing telemetry.

Provenance & limitations
  • Model identity (SHA-256, declared type/parameter count) comes from the model file's own bytes and llama-bench's own GGUF parsing — see /data for the exact hashes.
  • Acceleration evidence above is parsed directly from llama.cpp's own log output for each run, not assumed from the hardware being present.
  • These measurements describe throughput on the specific standard-ai-v0.1 workload only — see Methodology for what this does and does not establish.