L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsOpenClawMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Guides

  • OpenClaw Guide
  • How-To Guides

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

Can RTX 5090 run Qwen/Qwen2.5-Coder-1.5B?

Runs Q432GB VRAM availableRequires 3GB+

RTX 5090 meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Coder-1.5B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

RTX 5090 can run Qwen/Qwen2.5-Coder-1.5B with Q4 quantization. At approximately 280 tokens/second, you can expect Excellent speed - conversational response times under 1 second.

You have 29GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q43GB32GB280.21 tok/s✅ Fits comfortably
Q85GB32GB223.22 tok/s✅ Fits comfortably
FP1611GB32GB108.71 tok/s✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X
192GB
695.37 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
626.20 tok/s
Price: —
AMD Instinct MI300X
192GB
572.57 tok/s
Price: —
AMD Instinct MI250X
128GB
517.32 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
505.79 tok/s
Price: —

More questions

RTX 5090 specs & pricingFull guide for Qwen/Qwen2.5-Coder-1.5BQwen/Qwen2.5-Coder-1.5B speed on RTX 5090Qwen/Qwen2.5-Coder-1.5B Q4 requirements