Can DeepSeek V4 Flash run on AMD Instinct MI325X 256GB?

YES — Runs Great

S99Excellent

○Estimated from fit model

DeepSeek V4 Flash needs ~185.8 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With NVFP4 quantization, expect ~94 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

NVFP4 (Medium quality) — 185.8 GB, 94.4 tok/s, Runs well

185.8 GB required256.0 GB available

73% VRAM used

Fit status

Runs well

Decode

94.4 tok/s

TTFT

2052 ms

Safe context

872K

Memory

185.8 GB / 256.0 GB

Memory breakdown

Weights158.0 GB

KV Cache1.3 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

See how fast it feelsDeepSeek V4 Flash on AMD Instinct MI325X 256GB
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: 94.4 tok/s decode · 2.1s TTFT (warm) · 236 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	S	Runs well	94.4 tok/s	1119 ms	872K
Coding	S	Runs well	94.4 tok/s	2052 ms	872K
Agentic Coding	S	Runs well	94.4 tok/s	2984 ms	872K
Reasoning	S	Runs well	94.4 tok/s	2425 ms	872K
RAG	S	Runs well	94.4 tok/s	3730 ms	872K

Quantization options

How DeepSeek V4 Flash (284B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	110.8 GB	Low	S88
Q3_K_S	3	139.2 GB	Low	S90
NVFP4	4	159.0 GB	Medium	S90
Q4_K_M	4	173.2 GB	Medium	S90
Q5_K_MBest for your GPU	5	204.5 GB	High	S90
Q6_K	6	232.9 GB	High	F0
Q8_0	8	303.9 GB	Very High	F0
F16	16	582.2 GB	Maximum	F0

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

Your hardware

More models your AMD Instinct MI325X 256GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen 3.5 397B A17B	397B	A	39.2 tok/s

Frequently asked questions

See all results for AMD Instinct MI325X 256GB See all hardware for DeepSeek V4 Flash

URL: https://willitrunai.com/can-run/deepseek-v4-flash-on-instinct-mi325x-256gb

⇱ DeepSeek V4 Flash on AMD Instinct MI325X 256GB? YES