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/gemma 2b/on NVIDIA GH200 96GB

Can it run?

Can NVIDIA GH200 96GB run gemma 2b?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

2655.7 tok/s

TTFT

350 ms

Safe context

120K

Memory

12.8 GB / 96.0 GB

Memory breakdown

Weights1.2 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom9.6 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well2655.7 tok/s350 ms240K
ChatCRuns well2655.7 tok/s350 ms60K
CodingCRuns well2655.7 tok/s350 ms120K
RAGCRuns well2655.7 tok/s350 ms240K
ReasoningCRuns well2655.7 tok/s350 ms120K

Quantization options

How gemma 2b (2B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
0.8 GB
LowD30
Q3_K_S
3
1.0 GB
LowD30
NVFP4
4
1.1 GB
MediumD30
Q4_K_M
4
1.2 GB
MediumD30
Q5_K_M
5
1.4 GB
HighD30
Q6_K
6
1.6 GB
HighD30
Q8_0
8
2.1 GB
Very HighD30
F16Best for your GPU
16
4.1 GB
MaximumD30

Get started

Upgrade options

Hardware that runs gemma 2b well

AppleMac Studio M3 Ultra 256GBBudget pick
C456.5 tok/s decode

 

See all results for NVIDIA GH200 96GBSee all hardware for gemma 2b