Can InternLM 20B run on Gaudi 3 128GB?

YES — Runs Great

B58Good

○Estimated from fit model

InternLM 20B needs ~46.4 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q5_K_M quantization, expect ~184 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) — 46.4 GB, 183.5 tok/s, Runs well

46.4 GB required128.0 GB available

36% VRAM used

Fit status

Runs well

Decode

183.5 tok/s

TTFT

1055 ms

Safe context

Memory

46.4 GB / 128.0 GB

Memory breakdown

Weights14.4 GB

KV Cache18.3 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsInternLM 20B on Gaudi 3 128GB
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: 183.5 tok/s decode · 1.1s TTFT (warm) · 459 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	183.5 tok/s	576 ms	8K
Coding	B	Runs well	183.5 tok/s	1055 ms	8K
Agentic Coding	B	Runs well	183.5 tok/s	1535 ms	8K
Reasoning	B	Runs well	183.5 tok/s	1247 ms	8K
RAG	B	Runs well	183.5 tok/s	1919 ms	8K

Quantization options

How InternLM 20B (20B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	C46
Q3_K_S	3	9.8 GB	Low	C46
NVFP4	4

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 Gaudi 3 128GB See all hardware for InternLM 20B

URL: https://willitrunai.com/can-run/internlm-20b-on-gaudi-3-128gb

⇱