Profile Model
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-
Install
/plugin marketplace add modular/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add modular/skills --skill profile-modelgit clone --depth 1 https://github.com/modular/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/profile-model ~/.claude/skills/profile-modelPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Profile a model on MAX This skill answers three questions about any model you can run on MAX, whether it's a built-in architecture or a custom one loaded with `--custom-architectures`: 1. **Is my GPU actually being used?** (utilization, memory, clocks) 2. **Where does my model spend the most time?** (which kernels / phases) 3. **Why is *this* kernel slow?** (occupancy, stalls, roofline) It works from a `pip` or `pixi` install of MAX, driving the public `max` CLI or a Python script. ## How to decide what to run Each question needs a deeper, more expensive capture than the last. Work from the cheapest check toward the most invasive, and let each result decide whether going deeper is even worth it — don't capture more than the question needs. 1. **Start with the utilization check**. If the GPU is idle or lightly loaded while the workload runs, the bottleneck is host-side (CPU, transfers, small batch) — stop and report that. A kernel trace won't tell you anything a busy GPU wouldn't. 2. **If the GPU is busy, capture a kernel breakdown**. This is the common case and usually the final answer: it shows which kernels dominate GPU time. 3. **Only if one kernel dominates and you need to know *why*, do a single-kernel deep dive** on that one kernel. Skip this unless a breakdown has already pointed at a specific kernel — it replays the kernel many times and is slow.
Details
- Skill name
profile-model- Repository
- modular/skills
- Path
profile-model/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Profile Model skill do?
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-
How do I install the Profile Model skill?
Claude Code plugin: /plugin marketplace add modular/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Profile Model popular?
It lives in modular/skills, which has 213 GitHub stars and 22 forks.
Related skills
Benchmark Model
213modular/skills
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garba
Debug Model
213modular/skills
Debug a MAX model that loads, compiles, serves, and generates tokens but whose output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges. Applies during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on "parity failure", "silent corruption", "logits match but tokens diverge", "top-1 mismatch", "greedy divergence", and "model serves but generates garbage". Not for
Eval Model
213modular/skills
Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.
Serve Model
213modular/skills
Serve a model with MAX's `max serve` command: set up the environment (pixi or uv with the max-nightly conda channel / nightly wheel index), point the server at a Hugging Face repo or local checkpoint, target a custom architecture with `--custom-architectures`, and pick the right serve flags for the model. Use this whenever the user wants to run, launch, start, or host a model on MAX, bring up an OpenAI-compatible endpoint, serve a custom/ported architecture, debug a `max serve` startup failure, or figure out which serve flags (devices, quantization-encoding, max-length, task, trust-remote-code
Migrate Max V2 to V3
213modular/skills
Use when migrating a MAX model from the V2 graph API (max.nn.legacy, TensorValue, explicit Graph construction) to ModuleV3 (max.nn, Tensor, F.lazy() + compile()). Triggers on: "migrate to ModuleV3", "port a max.nn.legacy model to max.experimental", "convert TensorValue to Tensor", "update my model to the V3 API", "ModuleV3 migration". Workflow: read the concept map, rewrite imports and __call__ signatures, and replace graph building with compile(weights=...). Align weight names with the new module hierarchy and move the KV cache unflatten into forward(). Port sharding to a DeviceMesh when the
Slm Governance
278qualixar/superlocalmemory
Governed-workspace behavior for SuperLocalMemory. Covers roles (admin/member/viewer) and company mode, who administers a company-mode workspace (a signed-in admin, or `slm team` on the SLM computer), `slm token show` in strict mode, what remote web apps can never see or change, retention and lifecycle settings, the audit trail, GDPR export and erasure, and how agents must behave when operating under workspace governance. The audit and retention tools need the power MCP profile. Agents must never bypass governance controls.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.