{
  "schema_version": "q36.laptop-matrix.v1",
  "status": "planned_not_executed",
  "quants": [
    "IQ4_XS",
    "Q3_K_M",
    "IQ2_M",
    "IQ1_M"
  ],
  "backends": [
    "llama.cpp",
    "Ollama"
  ],
  "runtime_profiles": [
    "stock",
    "optimized"
  ],
  "primary_model": "Q36-v2 (same weights formerly released as v1.3)",
  "baseline_models": [
    "Huihui original",
    "Qwen/Qwen3.8-27B"
  ],
  "primary_cells": 16,
  "potential_all_model_cells": 48,
  "baseline_quant_availability": "not_verified_do_not_substitute_different_quants_silently",
  "gpu_jobs_authorized": false,
  "downloads_started": false,
  "profiles": {
    "stock": "Backend defaults explicitly recorded, with same context, prompt, output and time budgets enforced. Not an undocumented historical server setup.",
    "optimized": "Tune CPU threads, batch sizes, GPU offload and supported KV cache/flash-attention on a disjoint tuning set; freeze per device/quant/backend before test. Never optimize on scored prompts."
  },
  "common_controls": [
    "Exact weights SHA256 and projector SHA256",
    "One immutable prompt/image manifest and renderer-specific chat-template capture",
    "Separate non-thinking controlled track from publisher-recommended thinking track",
    "Same sampling, output cap, context, per-request deadline across comparable cells",
    "One warmup excluded; three text throughput repetitions; quality one trial except separately named pass@3 tests",
    "AC power, power mode, driver, runtime versions, thermals and throttling logged",
    "Randomized balanced cell order; cooldown after sustained thermal throttling",
    "No concurrent workloads; restart server between cells; clear/reuse caches explicitly",
    "Keep runtime profile independent from model identity (stock model vs stock runtime are different axes)"
  ],
  "metrics": [
    "prompt eval tokens/s",
    "decode tokens/s",
    "end-to-end tokens/s for matched IDs and length bins",
    "first visible output seconds (client) and TTFT if native provided",
    "request p50/p95 and total wall time",
    "prompt/completion token counts and missing usage",
    "process CPU percent 100%=one logical core",
    "process RSS, private/anonymous bytes if available, system commit, page faults, swap",
    "VRAM, GPU utilization, power, temperature, thermal limits",
    "content score, protocol score, refusal review, timeout/truncation/loop flags"
  ],
  "memory_policy": "Fail fast on insufficient memory; classify not runnable/OOM, not wrong answer. No model file size presented as total RAM need.",
  "cost_policy": "Preparation/API metadata/local analysis only; no inference provider, remote jobs or paid judge calls without separate authorization."
}