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.

  1. Home
  2. Models
  3. trl-internal-testing/tiny-LlamaForCausalLM-3.2
  4. Speed on NVIDIA H200 SXM 141GB
NVIDIA H200 SXM 141GB~733 tok/s (Q4)

trl-internal-testing/tiny-LlamaForCausalLM-3.2 speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for trl-internal-testing/tiny-LlamaForCausalLM-3.2 running on NVIDIA H200 SXM 141GB.

Speed Snapshot
Topline estimate from compatibility data
Modeltrl-internal-testing/tiny-LlamaForCausalLM-3.2
GPUNVIDIA H200 SXM 141GB
Q4 speed733 tok/s
Q4 VRAM required4GB
Data Source
Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Open full compatibility report

Quantization Speed Table

QuantizationVRAM neededVRAM availableSpeedVerdict
Q44GB141GB733 tok/s✅ Fits
Q87GB141GB503 tok/s✅ Fits
FP1615GB141GB273 tok/s✅ Fits
Back to trl-internal-testing/tiny-LlamaForCausalLM-3.2Q4 requirement pageFull compatibility breakdown