Partly — gemma-3-27b-it at Q4 fits the RX 7900 XT 20GB (20 GB GDDR6) at 4K context (≈ 18.81 GB) but not at the default 8K (≈ 21.55 GB needed). Use a shorter context or partial offload. Decode at Q4/8K: ≈ 45.6 tok/s (estimated, batch 1). FP16 needs ≈ 61.28 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.
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).