Can DeepSeek V2.5 236B run on AMD Instinct MI325X 256GB?

YES — Tight Fit

S88Excellent

○Estimated from fit model

DeepSeek V2.5 236B needs ~229.1 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~82 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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

Q4_K_M (Medium quality) — 229.1 GB, 82.0 tok/s, Tight fit

229.1 GB required256.0 GB available

89% VRAM used

Fit status

Tight fit

Decode

82.0 tok/s

TTFT

2362 ms

Safe context

23K

Memory

229.1 GB / 256.0 GB

Memory breakdown

Weights144.0 GB

KV Cache58.6 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

See how fast it feelsDeepSeek V2.5 236B 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: 82.0 tok/s decode · 2.4s TTFT (warm) · 205 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	82.0 tok/s	1288 ms	23K
Coding	S	Tight fit	82.0 tok/s	2362 ms	23K
Agentic Coding	A	Very compromised (needs ~15.8 GB host RAM)	48.1 tok/s	5854 ms	23K
Reasoning	S	Tight fit	82.0 tok/s	2791 ms	23K
RAG	A	Very compromised (needs ~15.8 GB host RAM)	48.1 tok/s	7318 ms	23K

Quantization options

How DeepSeek V2.5 236B (236B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	92.0 GB	Low	A78
Q3_K_S	3	115.6 GB	Low	A80
NVFP4	4	132.2 GB	Medium	A81
Q4_K_M	4	144.0 GB	Medium	A82
Q5_K_M	5	169.9 GB	High	A82
Q6_KBest for your GPU	6	193.5 GB	High	A82
Q8_0	8	252.5 GB	Very High	F0
F16	16	483.8 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek V2.5 236B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "deepseek-ai/DeepSeek-V2.5" \
 --hf-file "DeepSeek-V2.5-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI325X 256GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen 3.5 397B A17B	397B	A	39.2 tok/s
👁 DeepSeek DeepSeek V4 Flash	284B	S	94.4 tok/s
👁 Meta Llama 4 Maverick 17B 128E	400B	A	37.9 tok/s

Frequently asked questions

See all results for AMD Instinct MI325X 256GB See all hardware for DeepSeek V2.5 236B

URL: https://willitrunai.com/can-run/deepseek-v2.5-236b-on-instinct-mi325x-256gb

⇱ DeepSeek V2.5 236B on AMD Instinct MI325X 256GB? TIGHT FIT