RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek vl2 tiny run on the RX 7900 XTX?

Yes. At 8K context the best fit is F16, using about 7.4 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~408 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits2178
3-bit (Q3_K_M)2.4 GB Fits1671
4-bit (Q4_K_M)2.8 GB Fits1336
5-bit (Q5_K_M)3.1 GB Fits1146
6-bit (Q6_K)3.5 GB Fits996
8-bit (Q8_0)4.2 GB Fits769
16-bit (F16/BF16)7.2 GB Fits408

• real GGUF file size. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

deepseek vl2 tiny on every GPU and Mac · Every model that runs on the RX 7900 XTX · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/deepseek-vl2-tiny), AMD specs. Data as of 2026-11-17.