Skip to content

Can Radeon RX 7900 XT run Gemma 4 E4B IT?

Comfortable: GGUF Q8_0 needs 8.7 GB at 4K, batch 1; headroom 11.3 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

No measured run for this pair. Sizing is an estimate, not a runtime test.

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M5.3ComfortableVerified file
GGUF Q8_08.7ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K8.7Comfortable
16K8.9Comfortable
32K9.2Comfortable
128K10.8Comfortable

Generation speed

GGUF Q8_0: 54–71 tok/s · Derived range

Other model / GPU pairs