Can Radeon Instinct MI350X run GTE-Qwen2 1.5B Instruct?

Yes, the Radeon Instinct MI350X has 288GB VRAM and GTE-Qwen2 1.5B Instruct requires approximately 0.8GB VRAM for Q4 quantization. Estimated inference speed: 8190 tokens/second.

✅ — Radeon Instinct MI350X Can Run GTE-Qwen2 1.5B Instruct

The Radeon Instinct MI350X packs 288GB VRAM. GTE-Qwen2 1.5B Instruct needs ~0.8GB. You're good to go.

✅ Plenty of headroom

Hardware Specs

GPU: Radeon Instinct MI350X
VRAM: 288 GB
Bandwidth: 8189.999999999999 GB/s
MSRP: $0

Model Requirements

Model: GTE-Qwen2 1.5B Instruct
Parameters: 1.5B
VRAM (Q4): ~0.8 GB
Context: 131,072

Estimated Performance

8190 tok/s

Estimated inference speed (Q4 quantization)

GTE-Qwen2 1.5B Instruct Details Radeon Instinct MI350X Specs

Try GTE-Qwen2 1.5B Instruct on a different GPU

Try another model on Radeon Instinct MI350X

Full compatibility matrix

✅ — Radeon Instinct MI350X Can Run GTE-Qwen2 1.5B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Try GTE-Qwen2 1.5B Instruct on a different GPU

Try another model on Radeon Instinct MI350X

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab

✅ — Radeon Instinct MI350X Can Run GTE-Qwen2 1.5B Instruct

Hardware Specs

Model Requirements

Estimated Performance

Try GTE-Qwen2 1.5B Instruct on a different GPU

Try another model on Radeon Instinct MI350X

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab