Can DeepSeek V4 Flash run on NVIDIA B200 180GB?

YES — With Offload

S96Excellent

○Estimated from fit model

DeepSeek V4 Flash needs ~179.3 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With NVFP4 quantization, expect ~132 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.

Capabilities:

Select quantization to explore

NVFP4 (Medium quality) — 178.2 GB, 144.8 tok/s, Runs with offload

178.2 GB required180.0 GB available

99% VRAM used

Fit status

Runs with offload

Decode

144.8 tok/s

TTFT

1337 ms

Safe context

38K

Memory

178.2 GB / 180.0 GB

Memory breakdown

Weights158.0 GB

KV Cache1.3 GB

Runtime0.9 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsDeepSeek V4 Flash 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: 144.8 tok/s decode · 1.3s TTFT (warm) · 362 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	S	Runs with offload	131.8 tok/s	801 ms	25K
Coding	S	Runs with offload	131.8 tok/s	1469 ms	25K
Agentic Coding	S	Runs with offload	111.8 tok/s	2518 ms	25K
Reasoning	S	Runs with offload	131.8 tok/s	1736 ms	25K
RAG	S	Runs with offload	111.8 tok/s	3147 ms	25K

Quantization options

How DeepSeek V4 Flash (284B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	110.8 GB	Low	S90
Q3_K_SBest for your GPU	3	139.2 GB	Low	S90

Get started

Copy-paste commands to run DeepSeek V4 Flash on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "deepseek-ai/DeepSeek-V4-Flash" \
 --hf-file "DeepSeek-V4-Flash-NVFP4.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for NVIDIA B200 180GB See all hardware for DeepSeek V4 Flash

URL: https://willitrunai.com/can-run/deepseek-v4-flash-on-b200-180gb

⇱