In the measurement queue

AMD Radeon RX 9070 XT

16 GB · RDNA4 gfx1201

We have not measured this card yet.

It is in the queue. Until then we show its spec and an estimate from our formula, clearly labelled.

An estimate, not a measurement

≈28–34t/s

before, estimate · Qwen3.8-27B UD-Q3_K_XL · after: soon

Memory
16GB
Bandwidth
640GB/s
Architecture
RDNA4 gfx1201
An estimate, not a measurement

What fits

The formula η · bandwidth / bytes per token, for stock llama.cpp. Once measured, real numbers replace it here.

The formula η · bandwidth / bytes per token, for stock llama.cpp. Once measured, real numbers replace it here. app/landing/src/lib/estimator.ts: decodeRange (η·BW/B, raport 04 §2.2.4), memoryNeed (raport 04 §2.2.4)app/landing/src/lib/data/gpus.jsonapp/landing/src/lib/data/models.json
  • Qwen3.8-27B UD-Q3_K_XL

    memory needed, estimate ≈ 88–91 % of the card's memory

    before, estimate ≈ 28–34 t/s

    after soon

Measured cards