Can DeepSeek R1 Distill 70B run on AMD Instinct MI325X 256GB?

YES — Runs Great

A74Great

Estimated from fit model

DeepSeek R1 Distill 70B needs ~74.1 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~103 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) — 74.1 GB, 111.6 tok/s, Runs well

74.1 GB required256.0 GB available

29% VRAM used

Fit status

Runs well

Decode

111.6 tok/s

TTFT

1736 ms

Safe context

131K

Memory

74.1 GB / 256.0 GB

Memory breakdown

Weights42.7 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 70B 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: 111.6 tok/s decode · 1.7s TTFT (warm) · 279 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	A	Runs well	111.6 tok/s	947 ms	131K
Coding	A	Runs well	102.6 tok/s	1887 ms	131K
Agentic Coding	A	Runs well	111.6 tok/s	2524 ms	131K
Reasoning	A	Runs well	111.6 tok/s	2051 ms	131K
RAG	A	Runs well	111.6 tok/s	3155 ms	131K

Quantization options

How DeepSeek R1 Distill 70B (70B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B64
Q3_K_S	3	34.3 GB	Low	B65
NVFP4	4	39.2 GB	Medium	B65
Q4_K_M	4	42.7 GB	Medium	B65
Q5_K_M	5	50.4 GB	High	B66
Q6_K	6	57.4 GB	High	B66
Q8_0	8	74.9 GB	Very High	B68
F16Best for your GPU	16	143.5 GB	Maximum	A74

Get started

Copy-paste commands to run DeepSeek R1 Distill 70B on your machine.

Run

ollama run deepseek-r1:70b

Your hardware

More models your AMD Instinct MI325X 256GB can run

Model	Params	Grade	Decode
Qwen 3.5 397B A17B	397B	A	39.2 tok/s
Devstral 2 123B Instruct	123B	S	63.5 tok/s
Qwen 3.5 122B A10B	122B	S	176.1 tok/s
DeepSeek V4 Flash	284B	S	94.4 tok/s
Mistral Small 4 119B	119B	S	190.9 tok/s

Frequently asked questions

Can AMD Instinct MI325X 256GB run DeepSeek R1 Distill 70B?

Yes, AMD Instinct MI325X 256GB can run DeepSeek R1 Distill 70B with a A grade (Runs well). Expected decode speed: 102.6 tok/s.

How much VRAM does DeepSeek R1 Distill 70B need?

DeepSeek R1 Distill 70B (70B parameters) requires approximately 74.1 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 Distill 70B?

The recommended quantization for DeepSeek R1 Distill 70B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 Distill 70B run at on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, DeepSeek R1 Distill 70B achieves approximately 102.6 tokens per second decode speed with a time-to-first-token of 1887ms using Q4_K_M quantization.

Can AMD Instinct MI325X 256GB run DeepSeek R1 Distill 70B for coding?

For coding workloads, DeepSeek R1 Distill 70B on AMD Instinct MI325X 256GB receives a A grade with 102.6 tok/s and 131K context.

What context window can DeepSeek R1 Distill 70B use on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, DeepSeek R1 Distill 70B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI325X 256GB See all hardware for DeepSeek R1 Distill 70B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-70b-on-instinct-mi325x-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: