Packets and recipes

The deployment variants of this family, at every maturity.

nemotron-cascade-2-30b-a3b-931b595B70-measured narrow baseline

Nemotron Cascade 2 30B-A3B Q4_K_M · TP1

Measured evidence: 50.9 tok/s on 1× B70 · rapid research snapshot

12 unique cold prompts, 128 output tokens, median tokens 1-100 after TTFT, server and request prompt caches disabled lab report — documents the result; not a step-by-step install guide

Evidence D of A–D

decodeTTFTTP1cache-zero strict suite

What has been classified

Dense scorecards summarize every declared combination; measured slices retain exact evidence links.

quant × TP

Exact measured revision and rapid runtime; TP2/4 are unmeasured gaps. Fixed: revision=nemotron-cascade-2-30b-a3b-931b595 · runtime=llama.cpp SYCL fdb1db877 · mtp=0.

✓ Measured1 card, Q4_K_M TP1·Q4_K_M50.9 tok/sreport · evidence

2 untested combinations

TP2·Q4_K_MTP4·Q4_K_M

Full matrix and exact selectors

Measured results

Every number links to its proof.

family data

Measured speed (quick lab check)

Q4_K_M · one B70 · f16 KV · ctx=2048 configured; this one point is not a context curve

Q4_K_M · tensor parallel cards 150.9tok/sDecode449.16msTTFTstrict rapid snapshot · promoted standalone row · evidence

Q4_K_Mmissing

evidence 1

Fine print

Nemotron Cascade hybrid attention/Mamba MoE, 52 layers. one measured Cascade 2 GGUF revision. Measurements, artifact hashes, outputs, quality decisions, and speed stay pinned to their exact recorded identity.

Many people at once Not measured

Multi-user (aggregate) throughput has not been measured for this family. The lab’s one measured sweep so far is in the multi-user report; the projection block below includes a projected users curve where a projection exists.

How much faster could this get? No projection

No projection is shown: this model is not in the ML Bottleneck catalog yet. The measured numbers above stand on their own.