RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 Coder 30B A3B Instruct run on the RTX A6000?

Yes. At 8K context the best fit is Q8_0, using about 31.7 GB of the 45.6 GB usable on the RTX A6000. Estimated speed ceiling: ~241 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.6 GB Fits11.9 GB Fits14.2 GB Fits23.2 GB Fits694
3-bit (Q3_K_M) •14.8 GB Fits15.1 GB Fits17.4 GB Fits26.4 GB Fits531
4-bit (Q4_K_M) •18.3 GB Fits18.7 GB Fits21.0 GB Fits30.0 GB Fits421
5-bit (Q5_K_M) •21.3 GB Fits21.7 GB Fits23.9 GB Fits32.9 GB Fits360
6-bit (Q6_K) •24.4 GB Fits24.8 GB Fits27.1 GB Fits36.1 GB Fits311
8-bit (Q8_0) •31.3 GB Fits31.7 GB Fits33.9 GB Fits42.9 GB Tight241
16-bit (F16/BF16) •58.0 GB No58.3 GB No60.6 GB No69.6 GB No—

• real GGUF file size from unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF. Speed is a bandwidth ceiling (768 GB/s), not a benchmark. Methodology.

More

Qwen3 Coder 30B A3B Instruct on every GPU and Mac · Every model that runs on the RTX A6000 · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-Coder-30B-A3B-Instruct), NVIDIA specs. Data as of 2026-11-17.