Sizing and capacity planners
Work out how much memory, how many GPUs, how much concurrency and how much queue a workload needs — from the formulas, with every term a field you control.
VRAM Requirement Calculator
Parameters, quantisation, context and batch size into the VRAM a model needs — with the weights, the KV cache and the overhead itemised separately.
Can I Run This Model?
Enter your card's memory and bandwidth and a model's shape, and get a fit verdict, the largest context that fits, and the memory-bandwidth ceiling on tokens per second.
Quantisation Trade-off Planner
For a VRAM budget, a model and a context length, the memory each quantisation level needs and the highest precision that still fits.
GPU Sizing for Concurrent Users
Concurrent requests, context length and a target token rate into a GPU count — with the memory limit and the bandwidth limit computed separately so you can see which one binds.
Throughput Planner
Target request rate, prompt and output lengths into required capacity, by converting each request into GPU-seconds of prefill and decode.
Rate Limit Capacity Planner
Your TPM and RPM allowances and your per-request token counts into the number of active users they support, and which of the two limits binds first.
Concurrency Planner
Little's law applied to LLM calls: arrival rate times time in flight gives the concurrent slots a workload needs, and what a limit you already have can sustain.
Queue Depth and Wait Time Estimator
Arrival rate, service time and worker count into the expected queueing delay, the chance of waiting at all, and the workers needed to hold a wait target.
Timeout Chooser
Paste your own latency samples and get percentiles, a timeout derived from p99, the share of requests it would cut, and the worst case once retries are included.
Retry Budget Planner
How much extra traffic and cost a retry policy adds on a normal day, how much failure it actually removes, and how far it multiplies load during an outage.
Vector Index Sizing
Works out how much RAM a vector index needs from its vector count, dimensions, precision and graph width — and how many nodes that is.
Embedding Backfill Time Estimator
Turns corpus size, batch size and your rate limits into the wall-clock time an embedding backfill takes, and names the limit that binds first.
Chunk Count Estimator
Takes a corpus through chunking to vectors to storage, including the tokens overlap makes you embed twice.
Cache Hit Rate Estimator
Estimates the hit rate a cache of a given size earns under a stated Zipf popularity model, and what that is worth against your own per-request costs.
Batch Window Planner
Converts a volume and a deadline into the throughput and worker count that make it, with the setup time and the safety margin counted.
Cold Start Impact Estimator
Derives the share of requests that hit a cold start from your traffic rate and idle timeout, and the percentile at which they start to dominate.
Context Budget Allocator
Splits a context window across the system prompt, tool schemas, retrieval, history and the current message, and says how many turns still fit.
Eval Run Cost and Time Estimator
Multiplies examples, models and repeats into calls, cost and wall clock — including the LLM judge, and including what it all costs per week in CI.
Fine-Tuning Run Planner
Estimates the hours, device-hours and memory a fine-tuning run needs from dataset size, epochs, model size and the hardware figures you supply.
Capacity Plan Generator
Eleven inputs produce one plan: peak concurrency from Little's Law, the queueing cost of your utilisation target, the rate limit that binds first, and the month growth reaches it.