AMD · 16 GB GDDR6 · 640 GB/s bandwidth ·
Google · 8.0B · model ctx up to 128K
Yes — the RX 9070 XT 16GB (16 GB GDDR6) can run gemma-4-E4B-it. At Q4 with the default 8K context it needs ≈ 7.0 GB VRAM (weights 4.4 GB + KV cache 1.6 GB + 1 GB runtime overhead), which fits within 16 GB. Decode at Q4/8K: ≈ 50.9 tok/s (estimated, batch 1). FP16 needs ≈ 18.6 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
6.2 GB
Yes
50.9est.
Q4
8K default
7.0 GB
Yes
50.9est.
Q4
32K
11.8 GB
Yes
50.9est.
FP16
4K
17.8 GB
No
32.3est.
FP16
8K default
18.6 GB
No
29.6est.
FP16
32K
23.4 GB
No
18.7est.
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured
anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s
means the model is far beyond this card (offload-only territory).