Can DeepSeek R1 Distill 70B run on AMD Instinct MI300A 128GB?

YES — Runs Great

A78Great

Estimated from fit model

DeepSeek R1 Distill 70B needs ~61.3 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~95 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) — 61.3 GB, 94.5 tok/s, Runs well

61.3 GB required128.0 GB available

48% VRAM used

Fit status

Runs well

Decode

94.5 tok/s

TTFT

2049 ms

Safe context

131K

Memory

61.3 GB / 128.0 GB

Memory breakdown

Weights42.7 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 70B on AMD Instinct MI300A 128GB
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: 94.5 tok/s decode · 2.0s 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	A	Runs well	94.5 tok/s	1118 ms	131K
Coding	A	Runs well	94.5 tok/s	2049 ms	131K
Agentic Coding	A	Runs well	94.5 tok/s	2980 ms	131K
Reasoning	A	Runs well	94.5 tok/s	2421 ms	131K
RAG	A	Runs well	94.5 tok/s	3725 ms	131K

Quantization options

How DeepSeek R1 Distill 70B (70B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B67
Q3_K_S	3	34.3 GB	Low	B68
NVFP4	4	39.2 GB	Medium	B69
Q4_K_M	4	42.7 GB	Medium	B69
Q5_K_M	5	50.4 GB	High	A71
Q6_K	6	57.4 GB	High	A72
Q8_0Best for your GPU	8	74.9 GB	Very High	A74
F16	16	143.5 GB	Maximum	F0

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 MI300A 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	53.8 tok/s
Qwen 3.5 122B A10B	122B	S	149.2 tok/s
Mistral Small 4 119B	119B	S	161.7 tok/s
GPT-OSS 120B	117B	S	56.5 tok/s
Command A 111B	111B	S	59.8 tok/s

Frequently asked questions

Can AMD Instinct MI300A 128GB run DeepSeek R1 Distill 70B?

Yes, AMD Instinct MI300A 128GB can run DeepSeek R1 Distill 70B with a A grade (Runs well). Expected decode speed: 94.5 tok/s.

How much VRAM does DeepSeek R1 Distill 70B need?

DeepSeek R1 Distill 70B (70B parameters) requires approximately 61.3 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 MI300A 128GB?

On AMD Instinct MI300A 128GB, DeepSeek R1 Distill 70B achieves approximately 94.5 tokens per second decode speed with a time-to-first-token of 2049ms using Q4_K_M quantization.

Can AMD Instinct MI300A 128GB run DeepSeek R1 Distill 70B for coding?

For coding workloads, DeepSeek R1 Distill 70B on AMD Instinct MI300A 128GB receives a A grade with 94.5 tok/s and 131K context.

What context window can DeepSeek R1 Distill 70B use on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, 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 MI300A 128GB 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-mi300a-128gb" 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

94.5 tok/s

1118 ms

131K

Coding

Runs well

94.5 tok/s

2049 ms

131K

Agentic Coding

Runs well

94.5 tok/s

2980 ms

131K

Reasoning

Runs well

94.5 tok/s

2421 ms

131K

RAG

Runs well

94.5 tok/s

3725 ms

131K

Quantization options

How DeepSeek R1 Distill 70B (70B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B67
Q3_K_S	3	34.3 GB	Low	B68
NVFP4	4	39.2 GB	Medium	B69
Q4_K_M	4	42.7 GB	Medium	B69
Q5_K_M	5	50.4 GB	High	A71
Q6_K	6	57.4 GB	High	A72
Q8_0Best for your GPU	8	74.9 GB	Very High	A74
F16	16	143.5 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

53.8 tok/s

Qwen 3.5 122B A10B

122B

149.2 tok/s

Mistral Small 4 119B

119B

161.7 tok/s

GPT-OSS 120B

117B

56.5 tok/s

Command A 111B

111B

59.8 tok/s

Frequently asked questions

Can AMD Instinct MI300A 128GB run DeepSeek R1 Distill 70B?

Yes, AMD Instinct MI300A 128GB can run DeepSeek R1 Distill 70B with a A grade (Runs well). Expected decode speed: 94.5 tok/s.

How much VRAM does DeepSeek R1 Distill 70B need?

DeepSeek R1 Distill 70B (70B parameters) requires approximately 61.3 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 MI300A 128GB?

On AMD Instinct MI300A 128GB, DeepSeek R1 Distill 70B achieves approximately 94.5 tokens per second decode speed with a time-to-first-token of 2049ms using Q4_K_M quantization.

Can AMD Instinct MI300A 128GB run DeepSeek R1 Distill 70B for coding?

For coding workloads, DeepSeek R1 Distill 70B on AMD Instinct MI300A 128GB receives a A grade with 94.5 tok/s and 131K context.

What context window can DeepSeek R1 Distill 70B use on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, 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.