RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Seed OSS 36B Instruct run on the RX 7900 XTX?

Yes. At 8K context the best fit is Q3_K_M, using about 19.1 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~54 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •14.4 GB Fits15.4 GB Fits21.4 GB Tight45.4 GB No71
3-bit (Q3_K_M) •18.1 GB Fits19.1 GB Fits25.1 GB No49.1 GB No54
4-bit (Q4_K_M) •22.0 GB Tight23.0 GB No29.0 GB No53.0 GB No—
5-bit (Q5_K_M) •25.5 GB No26.5 GB No32.5 GB No56.5 GB No—
6-bit (Q6_K) •29.3 GB No30.3 GB No36.3 GB No60.3 GB No—
8-bit (Q8_0) •37.5 GB No38.5 GB No44.5 GB No68.5 GB No—
16-bit (F16/BF16) •69.0 GB No70.0 GB No76.0 GB No100 GB No—

• real GGUF file size from unsloth/Seed-OSS-36B-Instruct-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

Seed OSS 36B Instruct 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 (ByteDance-Seed/Seed-OSS-36B-Instruct), AMD specs. Data as of 2026-11-17.