~/best-gpu-for/qwen-3-30b-a3b
Alibaba provider

Best GPU for Qwen3 30B A3B

Ranked recommendations from the 42-GPU catalog for running Qwen3 30B A3B (30.5B params). Top picks by quality, then by cost.

Top picks.

$ ./rank --by quality
Tightest budget
RTX 3090
24GB · runs at Q4_K_M
17 GB weights · 1.6 GB headroom
Best quality
H100 80GB
80GB · runs at FP16/BF16
smallest card supporting the best available quant
Apple Silicon
M2 Max 64
64GB · runs at Q8_0
smallest M-series that fits
Datacenter (FP16 ambition)
H100 80GB
80GB · runs at FP16/BF16
best-quality datacenter card that fits

Full ranked list.

$ ./vrambudget --rank qwen-3-30b-a3b
GPUVRAMBest quantWeights at 15% safetyFit
nvidiaH100 80GB80GBFP16/BF16
61fitsappleM3 Max 9696GBFP16/BF16
61fitsnvidiaRTX Pro 600096GBFP16/BF16
61fitsappleM4 Max 128128GBFP16/BF16
61fitsappleM5 Max 128128GBFP16/BF16
61fitsnvidiaDGX Spark128GBFP16/BF16
61fitsintelGaudi 3128GBFP16/BF16
61fitsnvidiaH200141GBFP16/BF16
61fitsnvidia2× H100 NVL188GBFP16/BF16
61fitsappleM2 Ultra 192192GBFP16/BF16
61fitsnvidiaB200192GBFP16/BF16
61fitsamdMI300X192GBFP16/BF16
61fitsappleM3 Ultra 512512GBFP16/BF16
61fitsnvidiaRTX A600048GBQ8_0
32fitsnvidiaRTX 6000 Ada48GBQ8_0
32fitsnvidiaL40S48GBQ8_0
32fitsamdRadeon Pro W790048GBQ8_0
32fitsappleM2 Max 6464GBQ8_0
32fits

Next steps.

$ ./next
$ checkCan I run Qwen3 30B A3B?see all quants →full quant matrix$ tuneTune the mathopen calculator →/calc?model=qwen-3-30b-a3b

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.