RigRoute LabsRigRoute ↗

← Hardware

System identity

Apple M1 Pro (32 GB unified memory)

Memory architecture

Apple M1 Pro — unified-memory (shared with system RAM, not a separate VRAM pool)

Memory architecture: Unified memory -- system RAM and GPU-visible memory are the same 32 GB pool, not a separate VRAM pool.
Source: docs/acceptance-m1-pro-v0.1.md; hardware.accelerators[0].memoryArchitecture in both accepted result.json files
Accepted benchmark runs
ModelContextPrompt processingGenerationAcceleration evidenceStatus
llama 8B Q4_08192190.39 tok/s27.92 tok/s33/33 layers offloaded to GPUPASS
qwen3 14B Q4_K - Medium819297.09 tok/s11.73 tok/s41/41 layers offloaded to GPUPASS
Backend

BLAS,MTL — target device: BLAS,MTL

Methodology version

standard-ai-v0.1

Environment
Host OSmacOS 26.6.2
CPUApple M1 Pro
Installed memory32 GB
llama.cpp / llama-bench0.5.0 (build 11146, commit 7fe450e19)
Backends compiledBLAS,CPU,MTL
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.