← AI Hashrate

Can RTX 4090D 24GB (China) run Phi-4?

NVIDIA · 24 GB GDDR6X · 1008 GB/s bandwidth · Microsoft · 14.7B · model ctx up to 16K

Yes — the RTX 4090D 24GB (China) (24 GB GDDR6X) can run Phi-4. At Q4 with the default 8K context it needs ≈ 12.03 GB VRAM (weights 8.09 GB + KV cache 2.94 GB + 1 GB runtime overhead), which fits within 24 GB. Decode at Q4/8K: ≈ 43.6 tok/s (estimated, batch 1). FP16 needs ≈ 33.34 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K10.56 GBYes43.6 est.
Q48K default12.03 GBYes43.6 est.
Q432K20.84 GBYes43.6 est.
FP164K31.87 GBNo19.4 est.
FP168K default33.34 GBNo17.8 est.
FP1632K42.16 GBNo11.1 est.

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).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededRTX 4090D 24GB (China) VRAM
Q48.09 GB2.94 GB1 GB12.03 GB24 GB
FP1629.4 GB2.94 GB1 GB33.34 GB24 GB

Other GPUs that run Phi-4

All GPUs for Phi-4 →

Other models for the RTX 4090D 24GB (China)

All models on the RTX 4090D 24GB (China) →