RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 4B Instruct 2507 run on the RTX 4070 Ti?

Yes. At 8K context the best fit is F16, using about 9.3 GB of the 11.4 GB usable on the RTX 4070 Ti. Estimated speed ceiling: ~63 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.8 GB Fits3.4 GB Fits6.7 GB Fits20.2 GB No302
3-bit (Q3_K_M) •3.2 GB Fits3.7 GB Fits7.1 GB Fits20.6 GB No243
4-bit (Q4_K_M) •3.6 GB Fits4.1 GB Fits7.5 GB Fits21.0 GB No202
5-bit (Q5_K_M) •3.9 GB Fits4.5 GB Fits7.9 GB Fits21.4 GB No174
6-bit (Q6_K) •4.3 GB Fits4.9 GB Fits8.3 GB Fits21.8 GB No152
8-bit (Q8_0) •5.2 GB Fits5.8 GB Fits9.2 GB Fits22.7 GB No118
16-bit (F16/BF16) •8.8 GB Fits9.3 GB Fits12.7 GB No26.2 GB No63

• real GGUF file size from unsloth/Qwen3-4B-Instruct-2507-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

Qwen3 4B Instruct 2507 on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-4B-Instruct-2507), NVIDIA specs. Data as of 2026-11-17.