Can Qwen3-Coder 480B A35B Instruct run on AMD Instinct MI325X 256GB?

Q: What should I upgrade first if Qwen3-Coder 480B A35B Instruct feels slow on AMD Instinct MI325X 256GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

YES — With NVFP4

A78Great

Estimated from fit model

Qwen3-Coder 480B A35B Instruct needs ~298.2 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With NVFP4 quantization, expect ~28 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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.

Qwen3-Coder 480B A35B Instruct at Q4_K_M needs 322.2 GB — too much for AMD Instinct MI325X 256GB (256.0 GB). Runs at NVFP4 (298.2 GB) with medium quality. 3 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 322.2 GB, exceeds 256.0 GB available

322.2 GB required256.0 GB available

126% VRAM needed

66.2 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

21.1 tok/s

TTFT

9172 ms

Safe context

Memory

322.2 GB / 256.0 GB

Offload

20%

Memory breakdown

Weights292.8 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen3-Coder 480B A35B Instruct 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: 21.1 tok/s decode · 9.2s TTFT (warm) · 53 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 38.0 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	21.3 tok/s	4956 ms	4K
Coding	F	Too heavy	19.3 tok/s	10032 ms	4K
Agentic Coding	F	Too heavy	20.7 tok/s	13593 ms	4K
Reasoning	F	Too heavy	21.1 tok/s	10840 ms	4K
RAG	F	Too heavy	20.7 tok/s	16991 ms	4K

Quantization options

How Qwen3-Coder 480B A35B Instruct (480B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	187.2 GB	Low	S86
Q3_K_S	3	235.2 GB	Low	F0

Get started

Copy-paste commands to run Qwen3-Coder 480B A35B Instruct on your machine.

Run

lms load Qwen3-Coder-480B-A35B-Instruct && lms server start

Upgrade options

Hardware that runs Qwen3-Coder 480B A35B Instruct well

AMD Instinct MI350X 288GBBest value

288 GB VRAM (+32)8000 GB/s (+2000)

Makes the model fit on the accelerator instead of staying completely out of reach.35.3 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 67%.

~$8,000 MSRP

Frequently asked questions

Can AMD Instinct MI325X 256GB run Qwen3-Coder 480B A35B Instruct?

Yes, AMD Instinct MI325X 256GB can run Qwen3-Coder 480B A35B Instruct at NVFP4 quantization (Very compromised (needs ~38 GB host RAM)). The recommended Q4_K_M requires 322.2 GB which exceeds available memory, but at NVFP4 it needs only 298.2 GB. Expected decode speed: 28.4 tok/s.

How much VRAM does Qwen3-Coder 480B A35B Instruct need?

Qwen3-Coder 480B A35B Instruct (480B parameters) requires approximately 322.2 GB at Q4_K_M quantization. On AMD Instinct MI325X 256GB, it fits at NVFP4 using 298.2 GB.

What is the best quantization for Qwen3-Coder 480B A35B Instruct?

The recommended quantization is Q4_K_M, but on AMD Instinct MI325X 256GB the best fitting quantization is NVFP4, which uses 298.2 GB.

What speed will Qwen3-Coder 480B A35B Instruct run at on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, Qwen3-Coder 480B A35B Instruct achieves approximately 28.4 tokens per second decode speed with a time-to-first-token of 6814ms using NVFP4 quantization.

Can AMD Instinct MI325X 256GB run Qwen3-Coder 480B A35B Instruct for coding?

For coding workloads, Qwen3-Coder 480B A35B Instruct on AMD Instinct MI325X 256GB receives a F grade with 19.3 tok/s and 4K context.

What context window can Qwen3-Coder 480B A35B Instruct use on AMD Instinct MI325X 256GB?

See all results for AMD Instinct MI325X 256GB See all hardware for Qwen3-Coder 480B A35B Instruct

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3-coder-480b-a35b-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: