Can Llama 3.1 405B run on NVIDIA B200 180GB?

YES — With Q2_K

A84Great

○Estimated from fit model

Llama 3.1 405B needs ~184.5 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q2_K quantization, expect ~32 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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.

Llama 3.1 405B at Q4_K_M needs 273.6 GB — too much for NVIDIA B200 180GB (180.0 GB). Runs at Q2_K (184.5 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 273.6 GB, exceeds 180.0 GB available

273.6 GB required180.0 GB available

152% VRAM needed

93.6 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

12.7 tok/s

TTFT

15228 ms

Safe context

Memory

273.6 GB / 180.0 GB

Offload

30%

Memory breakdown

Weights247.1 GB

KV Cache7.7 GB

Runtime0.9 GB

Headroom18.0 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsLlama 3.1 405B on NVIDIA B200 180GB
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: 12.7 tok/s decode · 15.2s TTFT (warm) · 32 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	13.0 tok/s	8114 ms	4K
Coding	F	Too heavy	12.7 tok/s	15228 ms	4K
Agentic Coding	F	Too heavy	12.1 tok/s	23186 ms	4K
Reasoning	F	Too heavy	12.7 tok/s	17996 ms	4K
RAG	F	Too heavy	12.1 tok/s	28982 ms	4K