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 L40S run dphn/dolphin-2.9.1-yi-1.5-34b?

Runs Q448GB VRAM availableRequires 17GB+

NVIDIA L40S meets the minimum VRAM requirement for Q4 inference of dphn/dolphin-2.9.1-yi-1.5-34b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

NVIDIA L40S can run dphn/dolphin-2.9.1-yi-1.5-34b with Q4 quantization. At approximately 59 tokens/second, you can expect Good speed - acceptable for interactive use.

You have 31GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q417GB48GB59.39 tok/s✅ Fits comfortably
Q835GB48GB44.38 tok/s✅ Fits comfortably
FP1670GB48GB20.65 tok/s❌ Not recommended

Suitable alternatives

AMD Instinct MI300X
192GB
276.56 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
252.48 tok/s
Price: —
NVIDIA H100 SXM5 80GB
80GB
189.42 tok/s
Price: —
AMD Instinct MI300X
192GB
169.78 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
169.06 tok/s
Price: —

More questions

NVIDIA L40S specs & pricingFull guide for dphn/dolphin-2.9.1-yi-1.5-34bdphn/dolphin-2.9.1-yi-1.5-34b speed on NVIDIA L40Sdphn/dolphin-2.9.1-yi-1.5-34b Q4 requirements