Can GB200 NVL72 run Qwen2.5 Coder 32B Instruct?

Yes, the GB200 NVL72 has 13824GB VRAM and Qwen2.5 Coder 32B Instruct requires approximately 17.6GB VRAM for Q4 quantization. Estimated inference speed: 157 tokens/second.

✅ — GB200 NVL72 Can Run Qwen2.5 Coder 32B Instruct

The GB200 NVL72 packs 13824GB VRAM. Qwen2.5 Coder 32B Instruct needs ~17.6GB. You're good to go.

✅ Plenty of headroom

Hardware Specs

GPU: GB200 NVL72
VRAM: 13824 GB
Bandwidth: 3350 GB/s
MSRP: $0

Model Requirements

Model: Qwen2.5 Coder 32B Instruct
Parameters: 32B
VRAM (Q4): ~17.6 GB
Context: 8,192

Estimated Performance

157 tok/s

Estimated inference speed (Q4 quantization)

Qwen2.5 Coder 32B Instruct Details GB200 NVL72 Specs

Try Qwen2.5 Coder 32B Instruct on a different GPU

Try another model on GB200 NVL72

Full compatibility matrix

✅ — GB200 NVL72 Can Run Qwen2.5 Coder 32B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Try Qwen2.5 Coder 32B Instruct on a different GPU

Try another model on GB200 NVL72

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab

✅ — GB200 NVL72 Can Run Qwen2.5 Coder 32B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Try Qwen2.5 Coder 32B Instruct on a different GPU

Try another model on GB200 NVL72

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab