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 SXM5 80GB run codellama/CodeLlama-34b-hf?

Runs Q480GB VRAM availableRequires 17GB+

NVIDIA H100 SXM5 80GB meets the minimum VRAM requirement for Q4 inference of codellama/CodeLlama-34b-hf. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

NVIDIA H100 SXM5 80GB can run codellama/CodeLlama-34b-hf with Q4 quantization. At approximately 166 tokens/second, you can expect Excellent speed - conversational response times under 1 second.

You have 63GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q417GB80GB166.34 tok/s✅ Fits comfortably
Q835GB80GB127.37 tok/s✅ Fits comfortably
FP1670GB80GB63.74 tok/s✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X
192GB
286.45 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
263.44 tok/s
Price: —
AMD Instinct MI300X
192GB
183.93 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
170.28 tok/s
Price: —
AMD Instinct MI250X
128GB
165.53 tok/s
Price: —

More questions

NVIDIA H100 SXM5 80GB specs & pricingFull guide for codellama/CodeLlama-34b-hfcodellama/CodeLlama-34b-hf speed on NVIDIA H100 SXM5 80GBcodellama/CodeLlama-34b-hf Q4 requirements