~/best-gpu-for/qwen-3-6-35b-a3b
Alibaba provider

Best GPU for Qwen 3.6 35B A3B

Ranked recommendations from the 42-GPU catalog for running Qwen 3.6 35B A3B (35B params). Top picks by quality, then by cost.

Top picks.

$ ./rank --by quality
Tightest budget
RTX 3090
24GB · runs at Q3_K_M
15 GB weights · 3.7 GB headroom
Best quality
M3 Max 96
96GB · 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)
H200
141GB · runs at FP16/BF16
best-quality datacenter card that fits

Full ranked list.

$ ./vrambudget --rank qwen-3-6-35b-a3b
GPUVRAMBest quantWeights at 15% safetyFit
appleM3 Max 9696GBFP16/BF16
70fitsnvidiaRTX Pro 600096GBFP16/BF16
70fitsappleM4 Max 128128GBFP16/BF16
70fitsappleM5 Max 128128GBFP16/BF16
70fitsnvidiaDGX Spark128GBFP16/BF16
70fitsintelGaudi 3128GBFP16/BF16
70fitsnvidiaH200141GBFP16/BF16
70fitsnvidia2× H100 NVL188GBFP16/BF16
70fitsappleM2 Ultra 192192GBFP16/BF16
70fitsnvidiaB200192GBFP16/BF16
70fitsamdMI300X192GBFP16/BF16
70fitsappleM3 Ultra 512512GBFP16/BF16
70fitsappleM2 Max 6464GBQ8_0
37fitsappleM3 Max 6464GBQ8_0
37fitsappleM4 Pro 6464GBQ8_0
37fitsappleM5 Pro 6464GBQ8_0
37fitsnvidiaH100 80GB80GBQ8_0
37fitsnvidiaRTX A600048GBFP8/INT8
35fits

Next steps.

$ ./next
$ checkCan I run Qwen 3.6 35B A3B?see all quants →full quant matrix$ tuneTune the mathopen calculator →/calc?model=qwen-3-6-35b-a3b

Discussion.

$ gh discussion list

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