Can InternLM 20B run on NVIDIA GH200 96GB?

YES — Runs Great

B59Good

○Estimated from fit model

InternLM 20B needs ~43.2 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q5_K_M quantization, expect ~230 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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

Q5_K_M (High quality) — 43.2 GB, 229.5 tok/s, Runs well

43.2 GB required96.0 GB available

45% VRAM used

Fit status

Runs well

Decode

229.5 tok/s

TTFT

844 ms

Safe context

Memory

43.2 GB / 96.0 GB

Memory breakdown

Weights14.4 GB

KV Cache18.3 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsInternLM 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: 229.5 tok/s decode · 844ms TTFT (warm) · 574 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	B	Runs well	229.5 tok/s	460 ms	8K
Coding	B	Runs well	229.5 tok/s	844 ms	8K
Agentic Coding	B	Runs well	229.5 tok/s	1227 ms	8K
Reasoning	B	Runs well	229.5 tok/s	997 ms	8K
RAG	B	Runs well	229.5 tok/s	1534 ms	8K

Quantization options

How InternLM 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	C47
Q3_K_S	3	9.8 GB	Low	C47
NVFP4	4	11.2 GB	Medium	C47
Q4_K_M	4	12.2 GB	Medium	C48
Q5_K_M	5	14.4 GB	High	C48
Q6_K	6	16.4 GB	High	C48
Q8_0	8	21.4 GB	Very High	C49
F16Best for your GPU	16	41.0 GB	Maximum	C52

Get started

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

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "internlm/internlm2_5-20b-chat" \
 --hf-file "internlm2_5-20b-chat-Q5_K_M.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for NVIDIA GH200 96GB See all hardware for InternLM 20B

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