Free preview

Numbers Worth Memorising

In one line: a handful of anchors turns a two-minute derivation into a ten-second one, and knowing them is the difference between estimating live and stalling.

Precision, in bytes per parameter

Everything about model memory starts here.

PrecisionBytesTypical use
FP324Rarely used for inference now
FP16 / BF162The serving default
FP81Increasingly common on recent hardware
INT81Quantised serving
INT40.5Aggressive quantisation, noticeable quality cost

The one to internalise: FP16 means bytes equals twice the parameter count. A 7B model is 14GB of weights. A 70B model is 140GB. You will use this constantly.

Accelerator capacity

You do not need a spec sheet, you need one anchor and the ability to scale from it.

H100         80 GB HBM
A100         40 or 80 GB
Anchor:      ~80 GB per card

From that single number, useful conclusions fall out immediately. A 70B model at FP16 needs 140GB of weights, which does not fit on one 80GB card — so it needs at least two, with tensor parallelism, before a single request has been served. A 7B model at 14GB fits comfortably with room left for cache.

That "does it fit on one card" question is the first thing to answer about any self-hosted model, because the answer changes the deployment from a process into a distributed system.

Tokens

AnchorValue
Tokens per English word~1.3
Words per token~0.75
Tokens per page of prose~500
Tokens in a typical chat turn50–200
Tokens in a RAG prompt with retrieved context2,000–8,000

The ratio to remember is roughly 4 characters per token, or three-quarters of a word. Everything else can be derived from it live.

Embedding dimensions

Model classDimensions
Small / efficient384
Common general-purpose768
Large1,024–1,536
Very large3,072

Use 768 as the default anchor and 1,536 when someone says "large". Combined with the bytes-per-value figure, this gives vector storage instantly: a million 768-dimension float32 vectors is 1e6 × 768 × 43GB before any index overhead.

The latency ladder, AI edition

The classic ladder still holds underneath. These are the operations the classic one does not have.

The shape to notice: everything before generation is measured in milliseconds, and generation is measured in seconds. That is why streaming exists — not as a nicety but because time-to-first-token is the only latency number a user actually experiences, and it can be two orders of magnitude better than time-to-last-token.

Throughput anchors

Rough, hardware- and model-dependent, and enough to reason with:

QuantityAnchor
Single-stream decode, 7B class~50–100 tokens/sec
Single-stream decode, 70B class~10–30 tokens/sec
Batched throughput gain10× or more over single stream
Human reading speed~5 tokens/sec

That last row is the useful one and it is easy to forget. A model generating 30 tokens per second is producing text about six times faster than a person reads it — so for a chat interface, generation speed past a certain point buys nothing, and the budget is better spent on time-to-first-token or on cost.

Price anchors

Prices move, so memorise the shape rather than the figures.

Small hosted model     ~$0.1-0.5 per million tokens
Frontier hosted model  ~$3-15 per million tokens
Spread between tiers   roughly 10-30x
Output vs input        output typically 3-5x the input price

The spread is the number that matters, because it is what makes routing worth designing. If cheap and expensive models differ by 20× and 80% of your traffic is simple, routing that 80% to the cheap tier cuts cost by roughly 75% — which is a bigger win than almost any other optimisation available.

Storage anchors

ItemSize
One float32 value4 bytes
One 768-dim float32 vector~3 KB
One million such vectors, raw~3 GB
HNSW index overhead1.5–2× the raw vectors
A page of text~2 KB

Key takeaway

Memorise the shape rather than the spec sheet: FP16 means two bytes per parameter, an accelerator holds roughly 80GB, a token is about three-quarters of a word, a default embedding is 768 dimensions, and hosted model tiers differ by 10–30× with output priced several times input. From those five, every other number in this chapter is a short derivation — and the price spread is what makes routing the highest-leverage cost optimisation available.

Next: token arithmetic, and why the prompt is usually the expensive half.

Enjoying the preview?

Create a free account to unlock the rest of this course, the in-browser judge, and live AI mock interviews.

Sign up free to continue