RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Phi 3 mini 4k instruct run on the RX 7900 XT?

Yes. At 8K context the best fit is F16, using about 10.6 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~105 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •3.3 GB Fits565
3-bit (Q3_K_M) •3.8 GB Fits409
4-bit (Q4_K_M) •4.2 GB Fits334
5-bit (Q5_K_M) •4.6 GB Fits284
6-bit (Q6_K) •4.9 GB Fits255
8-bit (Q8_0) •5.7 GB Fits197
16-bit (F16/BF16)9.1 GB Fits105

• real GGUF file size from bartowski/Phi-3.1-mini-4k-instruct-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

More

Phi 3 mini 4k instruct on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (microsoft/Phi-3-mini-4k-instruct), AMD specs. Data as of 2026-11-17.