Case Studies
Small, self-contained experiments run directly on the DGX Sparks. Each one isolates a single variable — a quantization scheme, a decode setting, a context length — and reports what actually moved, with the numbers.
draft
How much does quantization hurt quality?
FP8 vs NVFP4 Laguna-S-2.1 on a fixed eval set — what 4-bit costs in correctness.
QuantizationOutput qualityMemory footprint
draft
How deep should you speculate?
Sweeping draft depth K=0..7 on GLM-5.2 across two DGX Sparks — where speculative decode stops paying, and why.
Speculative decodeDecode speedConcurrencyPower & efficiency
draft
Can you move the speculative drafter onto another machine?
Measuring what a remote drafter would cost and free — the wire, the draft time, and the reason the experiment stalled.
InterconnectSpeculative decodeDecode speedMemory footprint
Can you quantize the drafter instead of moving it?
The dspark speculator is a weight read. Shrinking it should buy most of a remote drafter's win, with no network involved.
QuantizationSpeculative decodeDecode speedMemory footprint
Does quantization actually buy you speed?
Decode, prefill, and power across precision levels on one DGX Spark.
QuantizationDecode speedPrefill / TTFTPower & efficiency