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 NVIDIA H100 PCIe 80GB run 01-ai/Yi-1.5-34B-Chat?

Runs Q480GB VRAM availableRequires 18GB+

NVIDIA H100 PCIe 80GB meets the minimum VRAM requirement for Q4 inference of 01-ai/Yi-1.5-34B-Chat. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

NVIDIA H100 PCIe 80GB can run 01-ai/Yi-1.5-34B-Chat with Q4 quantization. At approximately 114 tokens/second, you can expect Excellent speed - conversational response times under 1 second.

You have 62GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q418GB80GB113.75 tok/s✅ Fits comfortably
Q835GB80GB77.95 tok/s✅ Fits comfortably
FP1670GB80GB44.69 tok/s✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X
192GB
249.89 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
244.01 tok/s
Price: —
AMD Instinct MI300X
192GB
185.13 tok/s
Price: —
NVIDIA H100 SXM5 80GB
80GB
174.60 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
166.01 tok/s
Price: —

More questions

NVIDIA H100 PCIe 80GB specs & pricingFull guide for 01-ai/Yi-1.5-34B-Chat01-ai/Yi-1.5-34B-Chat speed on NVIDIA H100 PCIe 80GB01-ai/Yi-1.5-34B-Chat Q4 requirements