Can DeepSeek V3.2 run on AMD Instinct MI350X 288GB?

YES — With Q2_K

S90Excellent

Estimated from fit model

DeepSeek V3.2 needs ~291.9 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q2_K quantization, expect ~44 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.

DeepSeek V3.2 at Q4_K_M needs 439.5 GB — too much for AMD Instinct MI350X 288GB (288.0 GB). Runs at Q2_K (291.9 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 439.5 GB, exceeds 288.0 GB available

439.5 GB required288.0 GB available

153% VRAM needed

151.5 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

14.0 tok/s

TTFT

13787 ms

Safe context

Memory

439.5 GB / 288.0 GB

Offload

30%

Memory breakdown

Weights409.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsDeepSeek V3.2 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: 14.0 tok/s decode · 13.8s TTFT (warm) · 35 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	14.1 tok/s	7512 ms	4K
Coding	F	Too heavy	14.0 tok/s	13787 ms	4K
Agentic Coding	F	Too heavy	14.0 tok/s	20098 ms	4K
Reasoning	F	Too heavy	14.0 tok/s	16293 ms	4K
RAG	F	Too heavy	14.0 tok/s	25122 ms	4K

Inference speed

DeepSeek V3.2 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DeepSeek V3.2 at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~3 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	3.0	Too big
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	2.5	Too big
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	2.4	Too big
RTX 5090 32GB	32 GB	Q4_K_M	2.0	Too big
RTX 4090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	2.0	Too big
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	2.0	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	2.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.0	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.0	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.0	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	2.0	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	2.0	Too big
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	2.0	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How DeepSeek V3.2 (671B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	261.7 GB	Low	F0
Q3_K_S	3	328.8 GB	Low	F0
NVFP4	4	375.8 GB	Medium	F0
Q4_K_M	4	409.3 GB	Medium	F0
Q5_K_M	5	483.1 GB	High	F0
Q6_K	6	550.2 GB	High	F0
Q8_0	8	718.0 GB	Very High	F0
F16	16	1375.6 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek V3.2 on your machine.

Run

ollama run deepseek-v3.2

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V3.2?

Yes, AMD Instinct MI350X 288GB can run DeepSeek V3.2 at Q2_K quantization (Runs with offload (needs ~3.5 GB host RAM)). The recommended Q4_K_M requires 439.5 GB which exceeds available memory, but at Q2_K it needs only 291.9 GB. Expected decode speed: 44.2 tok/s.

How much VRAM does DeepSeek V3.2 need?

DeepSeek V3.2 (671B parameters) requires approximately 439.5 GB at Q4_K_M quantization. On AMD Instinct MI350X 288GB, it fits at Q2_K using 291.9 GB.

What is the best quantization for DeepSeek V3.2?

The recommended quantization is Q4_K_M, but on AMD Instinct MI350X 288GB the best fitting quantization is Q2_K, which uses 291.9 GB.

What speed will DeepSeek V3.2 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V3.2 achieves approximately 44.2 tokens per second decode speed with a time-to-first-token of 4381ms using Q2_K quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V3.2 for coding?

For coding workloads, DeepSeek V3.2 on AMD Instinct MI350X 288GB receives a F grade with 14.0 tok/s and 4K context.

What context window can DeepSeek V3.2 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V3.2 can safely use up to 4K tokens of context at Q2_K quantization. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if DeepSeek V3.2 feels slow on AMD Instinct MI350X 288GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek V3.2

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-v3.2-671b-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

Too heavy

14.1 tok/s

7512 ms

Coding

Too heavy

14.0 tok/s

13787 ms

Agentic Coding

Too heavy

14.0 tok/s

20098 ms

Reasoning

Too heavy

14.0 tok/s

16293 ms

RAG

Too heavy

14.0 tok/s

25122 ms

DeepSeek V3.2 inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

3.0

Too big

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

2.5

Too big

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

2.4

Too big

RTX 5090 32GB

32 GB

Q4_K_M

2.0

Too big

RTX 4090 24GB

24 GB

Q4_K_M

2.0

Too big

RTX 4080 Super 16GB

16 GB

Q4_K_M

2.0

Too big

RTX 3090 24GB

24 GB

Q4_K_M

2.0

Too big

RTX 4070 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 3060 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.0

Too big

RX 7900 XTX 24GB

24 GB

Q4_K_M

2.0

Too big

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

2.0

Too big

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

2.0

Too big

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

2.0

Too big

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

2.0

Too big

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

2.0

Too big

2× RTX 4090 24GB

48 GB

Q4_K_M

2.0

Too big

2× RTX 3090 24GB

48 GB

Q4_K_M

2.0

Too big

2× RX 7900 XTX 24GB

48 GB

Q4_K_M

2.0

Too big

4× RTX 3060 12GB

48 GB

Q4_K_M

2.0

Too big

Quantization options

How DeepSeek V3.2 (671B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	261.7 GB	Low	F0
Q3_K_S	3	328.8 GB	Low	F0
NVFP4	4	375.8 GB	Medium	F0
Q4_K_M	4	409.3 GB	Medium	F0
Q5_K_M	5	483.1 GB	High	F0
Q6_K	6	550.2 GB	High	F0
Q8_0	8	718.0 GB	Very High	F0
F16	16	1375.6 GB	Maximum	F0

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V3.2?

How much VRAM does DeepSeek V3.2 need?

DeepSeek V3.2 (671B parameters) requires approximately 439.5 GB at Q4_K_M quantization. On AMD Instinct MI350X 288GB, it fits at Q2_K using 291.9 GB.

What is the best quantization for DeepSeek V3.2?

The recommended quantization is Q4_K_M, but on AMD Instinct MI350X 288GB the best fitting quantization is Q2_K, which uses 291.9 GB.

What speed will DeepSeek V3.2 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V3.2 achieves approximately 44.2 tokens per second decode speed with a time-to-first-token of 4381ms using Q2_K quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V3.2 for coding?

For coding workloads, DeepSeek V3.2 on AMD Instinct MI350X 288GB receives a F grade with 14.0 tok/s and 4K context.

What context window can DeepSeek V3.2 use on AMD Instinct MI350X 288GB?

What should I upgrade first if DeepSeek V3.2 feels slow on AMD Instinct MI350X 288GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.