System identity

AMD Radeon RX 9070 (16 GB dedicated VRAM)

Memory architecture

AMD Radeon(TM) Graphics — unknown

AMD Radeon RX 9070 — unknown

Dedicated VRAM: 16 GB (16304 MiB reported free+used).

Source: llama-bench's own Vulkan device query (`llama-bench --list-devices`), recorded in docs/acceptance-rx9070-v0.1.md. NOT from Windows WMI's Win32_VideoController.AdapterRAM, which is a known 32-bit field that truncates for cards >=4GB -- it reported ~4 GB for this real 16 GB card. The structured result.json's own hardware.accelerators[1].dedicatedVramBytes is honestly "UNKNOWN" for exactly this reason; this figure is documented, provenanced evidence, not a value pulled from that field.

Accepted benchmark runs

Model	Context	Prompt processing	Generation	Acceleration evidence	Status
llama 8B Q4_0	8192	2511.81 tok/s	102.31 tok/s	33/33 layers offloaded to GPU	PASS
qwen3 14B Q4_K - Medium	8192	1177.22 tok/s	56.38 tok/s	41/41 layers offloaded to GPU	PASS

Backend

Vulkan — target device: AMD Radeon RX 9070 (targeted via -dev Vulkan1; Vulkan)

Methodology version

standard-ai-v0.1

Environment

Host OS	Microsoft Windows 11 Pro 10.0.26200
CPU	AMD Ryzen 7 9800X3D 8-Core Processor
Installed memory	31 GB
llama.cpp / llama-bench	0.5.0-dev (build 11146, commit 7fe450e19)
Backends compiled	CPU,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.