What GPU do you need to run Qwen3-Coder-30B-A3B-Instruct?

30.53B parameters, 3.3B active (mixture-of-experts) (Hugging Face, accessed 2026-10-16). Q4_K_M GGUF: 18.56 GB (source).

Single GPU that fits	VRAM	Speed estimate	Price
NVIDIA GeForce RTX 4090	24 GB	~383 tok/s	low $3,200, avg $4,663 (used) source, 2026-10-16
NVIDIA GeForce RTX 3090 Ti	24 GB	~383 tok/s	check price
NVIDIA GeForce RTX 3090	24 GB	~355 tok/s	low $1,889, avg $2,404 (used) source, 2026-10-16
AMD Radeon RX 7900 XTX	24 GB	~364 tok/s	low $1,350, avg $1,552 (new) source, 2026-10-16
NVIDIA Tesla P40	24 GB	~131 tok/s	check price
NVIDIA GeForce RTX 5090	32 GB	~678 tok/s	low $6,500, avg $8,757 (new) source, 2026-10-16
AMD Radeon AI PRO R9700	32 GB	~244 tok/s	check price
Apple Mac Studio M5 Max (32-core GPU, 36 GB)	36 GB	~174 tok/s	low $2,499 (new) source, 2026-10-16
NVIDIA RTX A6000	48 GB	~291 tok/s	low $6,170 (new) source, 2026-10-16
NVIDIA RTX 6000 Ada Generation	48 GB	~364 tok/s	check price
Apple Mac Studio M5 Max (40-core GPU, 64 GB)	64 GB	~233 tok/s	check price
Apple Mac Studio M5 Ultra (64-core GPU, 96 GB)	96 GB	~455 tok/s	check price
Framework Desktop, AMD Ryzen AI Max+ PRO 495 (Strix Halo), 192 GB	192 GB	~103 tok/s	low $6,799 (new) source, 2026-10-16

Speed calculator estimate

GPU Count Model

Estimate = 0.76 × bandwidth ÷ GB read per token (Q4 file size, scaled by active/total parameters for MoE). Fit = file size + 1.5 GB headroom ≤ total VRAM. Multi-GPU: VRAM adds, speed uses one card's bandwidth (layer split). Short context only. How this works

Build that fits it: 24 GB: one used RTX 3090
Build that fits it: 32 GB: two Radeon RX 9070
Build that fits it: 48 GB: dual used RTX 3090
Guide: Can an RTX 5060 Ti 16 GB run Qwen3 Coder 30B?

What GPU do you need to run Qwen3-Coder-30B-A3B-Instruct?

Speed calculator estimate

Related