Category:Engineering · Sub-category: devops · Last updated:
SLA-first GPU capacity sizing for a serving deployment: given a tokens-per-minute (TPM) target AND the interactivity SLA (output tokens/s/user), compute the pods and GPUs needed from a model's measured tok/s/user-vs-concurrency curve. Sizing MUST start from the tok/s/user SLA, not the TPM number alone: the SLA picks the concurrency, which sets per-pod throughput, which sets the GPU count. Also translates validated optimizations into delta-GPUs at the SLA-pinned concurrency. Backed by the standalone capacity_sizing.py tool. Use to answer "how many GPUs for N TPM", "size this for the customer", "pods for the SLA", or to sanity-check a sizing. Triggers on "capacity sizing", "how many GPUs", "how many pods", "tokens per minute sizing", "TPM target", "size for the customer", "interactivity SLA", "tokens per second per user", "GPU count for throughput", or any combination of "size / capacity / how-many" with "GPU / pod / TPM / SLA / tok-per-user / concurrency".
About this skill (catalog notes)
Inference Capacity Sizing includes pricing or quota commentary; at least one code block. The SKILL.md runs to about 904 words, in the catalog's typical mid-range.
License
MIT
Original author
cfregly
Indexed lastmod
Catalog position
Engineering · devops
Indexed related skills
10
How Inference Capacity Sizing fits the catalog
Inference Capacity Sizing sits in the Engineering category under the devops sub-topic in the ClaudSkills catalog. There are 10 related skills indexed alongside it; comparing a few before installing usually reveals which fits your workflow best.
These notes are auto-generated from features detected in the SKILL.md file and from this catalog's structure — they aren't part of the source repository.
What this skill does
Inference Capacity Sizing is a community-contributed Claude Code skill in the devops sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/inference-capacity-sizing/ and loads when your prompt matches the skill's trigger.
Who uses this skill
The Inference Capacity Sizing Claude Code skill is built for software engineers, backend developers, full-stack teams, and technical leads building and maintaining production systems. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 117,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
Or just download SKILL.md directly and drop it into ~/.claude/skills/inference-capacity-sizing/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/inference-capacity-sizing/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\inference-capacity-sizing\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
How do I install the Inference Capacity Sizing Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/inference-capacity-sizing/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Inference Capacity Sizing skill do?
SLA-first GPU capacity sizing for a serving deployment: given a tokens-per-minute (TPM) target AND the interactivity SLA (output tokens/s/user), compute the pods and GPUs needed from a model's measured tok/s/user-vs-concurrency curve. Sizing MUST start from the tok/s/user SLA, not the TPM number alone: the SLA picks the concurrency, which sets per-pod throughput, which sets the GPU count. Also translates validated optimizations into delta-GPUs at the SLA-pinned concurrency. Backed by the standalone capacity_sizing.py tool. Use to answer "how many GPUs for N TPM", "size this for the customer", "pods for the SLA", or to sanity-check a sizing. Triggers on "capacity sizing", "how many GPUs", "how many pods", "tokens per minute sizing", "TPM target", "size for the customer", "interactivity SLA", "tokens per second per user", "GPU count for throughput", or any combination of "size / capacity / how-many" with "GPU / pod / TPM / SLA / tok-per-user / concurrency".
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Inference Capacity Sizing skill?
Use Inference Capacity Sizing when your Claude Code task falls under the Engineering category — specifically in the devops area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Inference Capacity Sizing" or describe the task and let Claude pick). Browse related skills at /category/engineering/.
What is a Claude Code skill and how does the Inference Capacity Sizing skill fit in?
A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Inference Capacity Sizing is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering category. Learn more at /learn/what-is-a-claude-skill/.
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Claude™ is a trademark of Anthropic PBC. ClaudSkills (also referred to as Claude Skills or Claude Code Skills Catalog) is an independent community-curated registry of SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.
Install ClaudSkills — browse 70k+ skills offline, one tap from your home screen.