Can Llama 3.1 405B run on AMD Instinct MI350X 288GB?

YES — With Offload

A84Great

○Estimated from fit model

Llama 3.1 405B needs ~284.4 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~26 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 284.4 GB, 25.9 tok/s, Runs with offload

284.4 GB required288.0 GB available

99% VRAM used

Fit status

Runs with offload

Decode

25.9 tok/s

TTFT

7488 ms

Safe context

23K

Memory

284.4 GB / 288.0 GB

Memory breakdown

Weights247.1 GB

KV Cache7.7 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsLlama 3.1 405B 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: 25.9 tok/s decode · 7.5s TTFT (warm) · 65 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	A	Runs with offload	25.9 tok/s	4084 ms	23K
Coding	A	Runs with offload	25.9 tok/s	7488 ms	23K
Agentic Coding	A	Runs with offload (needs ~3.5 GB host RAM)	18.8 tok/s	14964 ms	23K
Reasoning	A	Runs with offload	25.9 tok/s	8849 ms	23K
RAG	A	Runs with offload (needs ~3.5 GB host RAM)	18.8 tok/s	18705 ms

Quantization options

How Llama 3.1 405B (405B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	158.0 GB	Low	A82
Q3_K_S	3	198.5 GB	Low	A82
NVFP4Best for your GPU

Get started

Copy-paste commands to run Llama 3.1 405B on your machine.

Run

ollama run llama3.1:405b

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen3-Coder 480B A35B Instruct	480B	A	35.3 tok/s

Frequently asked questions

See all results for AMD Instinct MI350X 288GB See all hardware for Llama 3.1 405B

URL: https://willitrunai.com/can-run/llama-3.1-405b-on-instinct-mi350x-288gb

⇱