Can AMD Instinct MI350X run Qwen2.5 Coder 32B Instruct?

Yes, the AMD Instinct MI350X has 288GB VRAM and Qwen2.5 Coder 32B Instruct requires approximately 17.6GB VRAM for Q4 quantization. Estimated inference speed: 281 tokens/second.

✅ — AMD Instinct MI350X Can Run Qwen2.5 Coder 32B Instruct

The AMD Instinct MI350X packs 288GB VRAM. Qwen2.5 Coder 32B Instruct needs ~17.6GB. You're good to go.

✅ Plenty of headroom

Hardware Specs

GPU: AMD Instinct MI350X
VRAM: 288 GB
Bandwidth: 6000 GB/s
MSRP: $15,000

Model Requirements

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

Estimated Performance

281 tok/s

Estimated inference speed (Q4 quantization)

Pricing

MSRP: $15,000

Qwen2.5 Coder 32B Instruct Details AMD Instinct MI350X Specs

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

Try another model on AMD Instinct MI350X

Full compatibility matrix

✅ — AMD Instinct MI350X Can Run Qwen2.5 Coder 32B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Pricing

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

Try another model on AMD Instinct MI350X

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab

✅ — AMD Instinct MI350X Can Run Qwen2.5 Coder 32B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Pricing

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

Try another model on AMD Instinct MI350X

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab