~/best-gpu-for/qwen-2-5-coder-32b
Alibaba provider

Best GPU for Qwen 2.5 Coder 32B

Ranked recommendations from the 42-GPU catalog for running Qwen 2.5 Coder 32B (32.5B params). Top picks by quality, then by cost.

Top picks.

$ ./rank --by quality
Tightest budget
RTX 3090
24GB · runs at AWQ 4-bit
17 GB weights · 1.5 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-2-5-coder-32b
GPUVRAMBest quantWeights at 15% safetyFit
appleM3 Max 9696GBFP16/BF16
65fitsnvidiaRTX Pro 600096GBFP16/BF16
65fitsappleM4 Max 128128GBFP16/BF16
65fitsappleM5 Max 128128GBFP16/BF16
65fitsnvidiaDGX Spark128GBFP16/BF16
65fitsintelGaudi 3128GBFP16/BF16
65fitsnvidiaH200141GBFP16/BF16
65fitsnvidia2× H100 NVL188GBFP16/BF16
65fitsappleM2 Ultra 192192GBFP16/BF16
65fitsnvidiaB200192GBFP16/BF16
65fitsamdMI300X192GBFP16/BF16
65fitsappleM3 Ultra 512512GBFP16/BF16
65fitsnvidiaRTX A600048GBQ8_0
35fitsnvidiaRTX 6000 Ada48GBQ8_0
35fitsnvidiaL40S48GBQ8_0
35fitsamdRadeon Pro W790048GBQ8_0
35fitsappleM2 Max 6464GBQ8_0
35fitsappleM3 Max 6464GBQ8_0
35fits

Next steps.

$ ./next
$ checkCan I run Qwen 2.5 Coder 32B?see all quants →full quant matrix$ tuneTune the mathopen calculator →/calc?model=qwen-2-5-coder-32b

Discussion.

$ gh discussion list

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