Can DeepSeek R1 Distill 70B run on H100 NVL 188GB?

YES — Runs Great

A76Great

○Estimated from fit model

DeepSeek R1 Distill 70B needs ~67.6 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~161 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) — 67.6 GB, 160.9 tok/s, Runs well

67.6 GB required188.0 GB available

36% VRAM used

Fit status

Runs well

Decode

160.9 tok/s

TTFT

1203 ms

Safe context

131K

Memory

67.6 GB / 188.0 GB

Memory breakdown

Weights42.7 GB

KV Cache4.9 GB

Runtime1.2 GB

Headroom18.8 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 70B on H100 NVL 188GB
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: 160.9 tok/s decode · 1.2s TTFT (warm) · 402 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	160.9 tok/s	656 ms	131K
Coding	A	Runs well	160.9 tok/s	1203 ms	131K
Agentic Coding	A	Runs well	160.9 tok/s	1750 ms	131K
Reasoning	A	Runs well	160.9 tok/s	1422 ms	131K
RAG	A	Runs well	160.9 tok/s	2188 ms	131K

Quantization options

How DeepSeek R1 Distill 70B (70B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B65
Q3_K_S	3	34.3 GB	Low	B66
NVFP4	4

Get started

Copy-paste commands to run DeepSeek R1 Distill 70B on your machine.

Run

ollama run deepseek-r1:70b

Your hardware

More models your H100 NVL 188GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	91.6 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S

Frequently asked questions

See all results for H100 NVL 188GB See all hardware for DeepSeek R1 Distill 70B

URL: https://willitrunai.com/can-run/deepseek-r1-70b-on-h100-nvl-188gb

⇱