Can Granite Code 20B run on NVIDIA GH200 96GB?

YES — Runs Great

A77Great

○Estimated from fit model

Granite Code 20B needs ~26.2 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~266 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 26.2 GB, 280.0 tok/s, Runs well

26.2 GB required96.0 GB available

27% VRAM used

Fit status

Runs well

Decode

280.0 tok/s

TTFT

691 ms

Safe context

Memory

26.2 GB / 96.0 GB

Memory breakdown

Weights12.2 GB

KV Cache3.2 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsGranite Code 20B on NVIDIA GH200 96GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
 """Sort a list using the quicksort algorithm.

 Args:
 arr: List of integers to sort.

 Returns:
 A new sorted list.
 """
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 280.0 tok/s decode · 691ms TTFT (warm) · 700 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	265.6 tok/s	398 ms	8K
Coding	A	Runs well	265.6 tok/s	729 ms	8K
Agentic Coding	A	Runs well	265.6 tok/s	1060 ms	8K
Reasoning	A	Runs well	265.6 tok/s	862 ms	8K
RAG	A	Runs well	265.6 tok/s	1325 ms	8K

Quantization options

How Granite Code 20B (20B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	B69
Q3_K_S	3	9.8 GB	Low	B69
NVFP4	4

Get started

Copy-paste commands to run Granite Code 20B on your machine.

Run

ollama run granite-code:20b

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	47 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S

Frequently asked questions

See all results for NVIDIA GH200 96GB See all hardware for Granite Code 20B

URL: https://willitrunai.com/can-run/granite-code-20b-on-gh200-96gb

⇱