howtospark

Training

18 methods · 1 recipe

The resources you can run out of

Required — does it fit?

Required
CapacitySpark128 GB

Can the weights fit — to load and transform them, and for the finished model to run. The gate on whether you can do anything at all.

Quality of life — how well does it run?

BandwidthSpark273 GB/s

Bytes streamed per token at decode — the Spark's ~273 GB/s LPDDR5x is the usual single-user bottleneck.

ComputeSpark1 PFLOP FP4

FLOPs — dominates prefill and large-batch serving.

KV cacheSparkshares 128 GB

Runtime state that grows with context × batch; binds at long context.

Family
Relieves
Stage
18 of 18 methods

Quantization

Fewer bits per number — weight-only, weight+activation, or KV.

FP4 microscaling

Hardware-coupled 4-bit block formats (MXFP4, NVFP4) for Blackwell.

Pruning / sparsity

Remove weights — unstructured, semi-structured (N:M), or structured.

Distillation

Train a smaller student to mimic a teacher.

Low-rank

SVD / adapters; often a quant-error compensation term.

KV compression

Compress runtime KV state, not the weights.