RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Yi 34B 200K run on the 2x RTX 4090?

Yes. At 8K context the best fit is Q8_0, using about 36.4 GB of the 45.6 GB usable on the 2x RTX 4090. Estimated speed ceiling: ~28 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •15.0 GB Fits16.0 GB Fits21.6 GB Fits44.1 GB Tight69
3-bit (Q3_K_M) •17.0 GB Fits17.9 GB Fits23.5 GB Fits46.0 GB No61
4-bit (Q4_K_M) •20.7 GB Fits21.6 GB Fits27.3 GB Fits49.8 GB No49
5-bit (Q5_K_M) •24.1 GB Fits25.0 GB Fits30.7 GB Fits53.2 GB No41
6-bit (Q6_K) •27.7 GB Fits28.7 GB Fits34.3 GB Fits56.8 GB No36
8-bit (Q8_0) •35.5 GB Fits36.4 GB Fits42.1 GB Tight64.6 GB No28
16-bit (F16/BF16)65.5 GB No66.5 GB No72.1 GB No94.6 GB No—

• real GGUF file size from TheBloke/Yi-34B-200K-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

More

Yi 34B 200K on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator

Data: Hugging Face Hub (01-ai/Yi-34B-200K), NVIDIA specs. Data as of 2026-11-17.