Can DeepSeek V2.5 236B run on AMD Instinct MI350X 288GB?

YES — Runs Great

S91Excellent

Estimated from fit model

DeepSeek V2.5 236B needs ~232.3 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~109 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

Q4_K_M (Medium quality) — 232.3 GB, 109.3 tok/s, Runs well

232.3 GB required288.0 GB available

81% VRAM used

Fit status

Runs well

Decode

109.3 tok/s

TTFT

1771 ms

Safe context

31K

Memory

232.3 GB / 288.0 GB

Memory breakdown

Weights144.0 GB

KV Cache58.6 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDeepSeek V2.5 236B on AMD Instinct MI350X 288GB
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: 109.3 tok/s decode · 1.8s TTFT (warm) · 273 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	109.3 tok/s	966 ms	31K
Coding	S	Runs well	109.3 tok/s	1771 ms	31K
Agentic Coding	S	Runs with offload (needs ~1.4 GB host RAM)	80.3 tok/s	3507 ms	31K
Reasoning	S	Runs well	109.3 tok/s	2094 ms	31K
RAG	S	Runs with offload (needs ~1.4 GB host RAM)	80.3 tok/s	4384 ms	31K

Quantization options

How DeepSeek V2.5 236B (236B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	92.0 GB	Low	A77
Q3_K_S	3	115.6 GB	Low	A79
NVFP4	4	132.2 GB	Medium	A80
Q4_K_M	4	144.0 GB	Medium	A81
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 MI350X 288GB can run

Model	Params	Grade	Decode
Qwen 3.5 397B A17B	397B	S	78.9 tok/s
DeepSeek V4 Flash	284B	S	125.8 tok/s
Qwen3-Coder 480B A35B Instruct	480B	A	35.3 tok/s
Llama 4 Maverick 17B 128E	400B	S	77.4 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V2.5 236B?

Yes, AMD Instinct MI350X 288GB can run DeepSeek V2.5 236B with a S grade (Runs well). Expected decode speed: 109.3 tok/s.

How much VRAM does DeepSeek V2.5 236B need?

DeepSeek V2.5 236B (236B parameters) requires approximately 232.3 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek V2.5 236B?

The recommended quantization for DeepSeek V2.5 236B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek V2.5 236B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V2.5 236B achieves approximately 109.3 tokens per second decode speed with a time-to-first-token of 1771ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V2.5 236B for coding?

For coding workloads, DeepSeek V2.5 236B on AMD Instinct MI350X 288GB receives a S grade with 109.3 tok/s and 31K context.

What context window can DeepSeek V2.5 236B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V2.5 236B can safely use up to 31K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek V2.5 236B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/deepseek-v2.5-236b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

109.3 tok/s

966 ms

31K

Coding

Runs well

109.3 tok/s

1771 ms

31K

Agentic Coding

Runs with offload (needs ~1.4 GB host RAM)

80.3 tok/s

3507 ms

31K

Reasoning

Runs well

109.3 tok/s

2094 ms

31K

RAG

Runs with offload (needs ~1.4 GB host RAM)

80.3 tok/s

4384 ms

31K

Quantization options

How DeepSeek V2.5 236B (236B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	92.0 GB	Low	A77
Q3_K_S	3	115.6 GB	Low	A79
NVFP4	4	132.2 GB	Medium	A80
Q4_K_M	4	144.0 GB	Medium	A81
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

Model

Params

Grade

Decode

Capabilities

Qwen 3.5 397B A17B

397B

78.9 tok/s

DeepSeek V4 Flash

284B

125.8 tok/s

Qwen3-Coder 480B A35B Instruct

480B

35.3 tok/s

Llama 4 Maverick 17B 128E

400B

77.4 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V2.5 236B?

Yes, AMD Instinct MI350X 288GB can run DeepSeek V2.5 236B with a S grade (Runs well). Expected decode speed: 109.3 tok/s.

How much VRAM does DeepSeek V2.5 236B need?

DeepSeek V2.5 236B (236B parameters) requires approximately 232.3 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek V2.5 236B?

The recommended quantization for DeepSeek V2.5 236B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek V2.5 236B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V2.5 236B achieves approximately 109.3 tokens per second decode speed with a time-to-first-token of 1771ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V2.5 236B for coding?

For coding workloads, DeepSeek V2.5 236B on AMD Instinct MI350X 288GB receives a S grade with 109.3 tok/s and 31K context.

What context window can DeepSeek V2.5 236B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V2.5 236B can safely use up to 31K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.