llmfit operator
When to use this skill
Use this skill for source-grounded, node-local model-fit decisions: hardware inventory, fit verdicts, score/ranking output, hardware profiles, plan and storage estimates, and read-only REST queries. It keeps formula-based estimates separate from measured inference.
Route generic service or inference performance tuning to performance-optimization. This checkout has no separate lmstudio-cli or typesafe-ai skill; treat those names only as llmfit provider/API values and use the pinned reference when needed.
Instructions
- Run the offline gate first. From the repository root run
python3 .agent-skills/llmfit/scripts/preflight.py --json; from an installed skill root run python3 "$SKILLS_ROOT/llmfit/scripts/preflight.py" --json. Add --repo PATH --expect-commit FULL_SHA only when checking a supplied source checkout. The helper never starts llmfit or invokes network/provider work.
- Establish binary and scope. Run
llmfit --version and llmfit --help; if unavailable, stop at an install/source-build handoff. Do not run an installer, package manager, cargo build, container pull, or model download without explicit approval.
- Capture read-only hardware evidence. Run
llmfit system --json; use llmfit doctor only for a diagnostic request. Load references/upstream.md for the pinned platform probe and capability matrix.
- Run a static fit query. Prefer
llmfit recommend --json --limit N (optionally a supported --use-case) or llmfit fit --json -n N; use llmfit info "MODEL" for one row. Keep tok/s, prefill, and TTFT labeled as estimates unless output explicitly reports measured confidence.
- Apply the source thresholds.
memory_required / memory_available gives Perfect at ≤0.60, Good at ≤0.85, Marginal at ≤0.98, and Too Tight above 0.98. recommended_ram_gb does not alter the verdict; offload paths cap at Good, and Too Tight is not a runnable claim. Consult the reference for estimation caveats.
- Compare capacity and plans consistently. Use global capacity overrides before
fit, or a validated hardware profile for speed-relevant simulation. For a named model use llmfit plan "MODEL" --context 8192 --json, keeping quantization/context fixed when comparing plan and fit. Storage output is capacity arithmetic, not free-disk evidence.
- Keep API and side effects distinct. A loopback
serve plus GET routes is read-only after an approved launch; /api/v1/plan is still an estimate. Downloads, TUI/provider pulls, llmfit bench, credentials/network, and --share PR creation require separate approval; use the pinned dry-run command for share payload preview.
- Return an evidence-backed conclusion. Include exact commands, host/profile/override inputs, model/quant/context, fit level/run mode, estimate basis/confidence, and whether a measured run occurred. Never report estimated throughput as a benchmark.
Examples
# Offline inventory before any upstream command
python3 .agent-skills/llmfit/scripts/preflight.py --json
# Read-only host inventory and top coding candidates
llmfit system --json
llmfit recommend --json --use-case coding --limit 5
# Capacity simulation and one reproducible model plan
llmfit --memory=24G --ram=64G --cpu-cores=16 fit --json -n 10
llmfit plan "Qwen/Qwen3-4B-MLX-4bit" --context 8192 --json
Best practices
- Preserve raw JSON alongside summaries as the audit trail for detected hardware and estimate provenance.
- Prefer validated profiles over capacity flags when memory bandwidth or fp16 throughput matters.
- Treat Perfect/Good/Marginal as fit pressure, not quality or speed guarantees; report run mode and confidence.
- Keep
doctor for bug reports and API access loopback-only unless an approved design says otherwise.
References
1---2name: llmfit3description: Operate AlexsJones/llmfit to inspect detected hardware, rank model fit, estimate plans and storage, run the local REST API, and separate formula-based estimates from measured inference. Use when a user asks what LLMs fit a machine, how much RAM/VRAM a model needs, which runtime is plausible, or whether a result is measured versus estimated. Do not use this skill to install binaries, pull models, benchmark a provider, or submit community results without explicit approval.4allowed-tools: Bash Read5compatibility: Requires a llmfit binary or source checkout; GPU/runtime availability is host-dependent.6license: MIT7metadata:8 version: "1.1.0"9 source: https://skillmd.com/skills/akillness/llmfit10 upstream: https://github.com/AlexsJones/llmfit11 upstream_commit: 4b9fdd9c5d1da3aa38ee5f7de872a5555c029a3e12---1314# llmfit operator1516## When to use this skill1718Use this skill for source-grounded, node-local model-fit decisions: hardware inventory, fit verdicts, score/ranking output, hardware profiles, plan and storage estimates, and read-only REST queries. It keeps formula-based estimates separate from measured inference.1920Route generic service or inference performance tuning to `performance-optimization`. This checkout has no separate `lmstudio-cli` or `typesafe-ai` skill; treat those names only as llmfit provider/API values and use the pinned reference when needed.2122## Instructions23241. **Run the offline gate first.** From the repository root run `python3 .agent-skills/llmfit/scripts/preflight.py --json`; from an installed skill root run `python3 "$SKILLS_ROOT/llmfit/scripts/preflight.py" --json`. Add `--repo PATH --expect-commit FULL_SHA` only when checking a supplied source checkout. The helper never starts llmfit or invokes network/provider work.252. **Establish binary and scope.** Run `llmfit --version` and `llmfit --help`; if unavailable, stop at an install/source-build handoff. Do not run an installer, package manager, `cargo build`, container pull, or model download without explicit approval.263. **Capture read-only hardware evidence.** Run `llmfit system --json`; use `llmfit doctor` only for a diagnostic request. Load [references/upstream.md](references/upstream.md) for the pinned platform probe and capability matrix.274. **Run a static fit query.** Prefer `llmfit recommend --json --limit N` (optionally a supported `--use-case`) or `llmfit fit --json -n N`; use `llmfit info "MODEL"` for one row. Keep tok/s, prefill, and TTFT labeled as estimates unless output explicitly reports measured confidence.285. **Apply the source thresholds.** `memory_required / memory_available` gives Perfect at ≤0.60, Good at ≤0.85, Marginal at ≤0.98, and Too Tight above 0.98. `recommended_ram_gb` does not alter the verdict; offload paths cap at Good, and Too Tight is not a runnable claim. Consult the reference for estimation caveats.296. **Compare capacity and plans consistently.** Use global capacity overrides before `fit`, or a validated hardware profile for speed-relevant simulation. For a named model use `llmfit plan "MODEL" --context 8192 --json`, keeping quantization/context fixed when comparing `plan` and `fit`. Storage output is capacity arithmetic, not free-disk evidence.307. **Keep API and side effects distinct.** A loopback `serve` plus GET routes is read-only after an approved launch; `/api/v1/plan` is still an estimate. Downloads, TUI/provider pulls, `llmfit bench`, credentials/network, and `--share` PR creation require separate approval; use the pinned dry-run command for share payload preview.318. **Return an evidence-backed conclusion.** Include exact commands, host/profile/override inputs, model/quant/context, fit level/run mode, estimate basis/confidence, and whether a measured run occurred. Never report estimated throughput as a benchmark.3233## Examples3435```sh36# Offline inventory before any upstream command37python3 .agent-skills/llmfit/scripts/preflight.py --json3839# Read-only host inventory and top coding candidates40llmfit system --json41llmfit recommend --json --use-case coding --limit 54243# Capacity simulation and one reproducible model plan44llmfit --memory=24G --ram=64G --cpu-cores=16 fit --json -n 1045llmfit plan "Qwen/Qwen3-4B-MLX-4bit" --context 8192 --json46```4748## Best practices4950- Preserve raw JSON alongside summaries as the audit trail for detected hardware and estimate provenance.51- Prefer validated profiles over capacity flags when memory bandwidth or fp16 throughput matters.52- Treat Perfect/Good/Marginal as fit pressure, not quality or speed guarantees; report run mode and confidence.53- Keep `doctor` for bug reports and API access loopback-only unless an approved design says otherwise.5455## References5657- [Pinned llmfit command, hardware, threshold, estimate, API, and safety matrix](references/upstream.md)58- [Upstream CLI documentation at the pinned commit](https://raw.githubusercontent.com/AlexsJones/llmfit/4b9fdd9c5d1da3aa38ee5f7de872a5555c029a3e/docs/cli.md)59- [Upstream scoring and estimate model](https://raw.githubusercontent.com/AlexsJones/llmfit/4b9fdd9c5d1da3aa38ee5f7de872a5555c029a3e/docs/how-it-works.md)60- [Upstream platform limits](https://raw.githubusercontent.com/AlexsJones/llmfit/4b9fdd9c5d1da3aa38ee5f7de872a5555c029a3e/docs/platform-support.md)61- [Upstream MIT license](https://raw.githubusercontent.com/AlexsJones/llmfit/4b9fdd9c5d1da3aa38ee5f7de872a5555c029a3e/LICENSE)