Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/Llama 3.3 70B/on NVIDIA H200 PCIe 141GB

Can it run?

Can NVIDIA H200 PCIe 141GB run Llama 3.3 70B?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

94.4 tok/s

TTFT

2050 ms

Safe context

33K

Memory

68.9 GB / 141.0 GB

Memory breakdown

Weights42.7 GB
KV Cache10.9 GB
Runtime1.2 GB
Headroom14.1 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well94.4 tok/s2982 ms56K
ChatCRuns well94.4 tok/s1118 ms18K
CodingCRuns well94.4 tok/s2050 ms33K
RAGCRuns well94.4 tok/s3728 ms56K
ReasoningCRuns well94.4 tok/s2423 ms33K

Quantization options

How Llama 3.3 70B (70B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
27.3 GB
LowD34
Q3_K_S
3
34.3 GB
LowD35
NVFP4
4
39.2 GB
MediumD35
Q4_K_M
4
42.7 GB
MediumD36
Q5_K_M
5
50.4 GB
HighD37
Q6_K
6
57.4 GB
HighD38
Q8_0Best for your GPU
8
74.9 GB
Very HighC41
F16
16
143.5 GB
MaximumF0

Get started

Ollama
ollama run llama-3.3-70b
HuggingFace
huggingface-cli download llama-3.3-70b
See all results for NVIDIA H200 PCIe 141GBSee all hardware for Llama 3.3 70B