Can Gemma 4 31B run on AMD Instinct MI350X 288GB?

YES — Runs Great

A83Great

Estimated from fit model

Gemma 4 31B needs ~63.1 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~204 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) — 63.1 GB, 203.5 tok/s, Runs well

63.1 GB required288.0 GB available

22% VRAM used

Fit status

Runs well

Decode

203.5 tok/s

TTFT

951 ms

Safe context

256K

Memory

63.1 GB / 288.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsGemma 4 31B 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: 203.5 tok/s decode · 951ms TTFT (warm) · 509 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	203.5 tok/s	519 ms	256K
Coding	A	Runs well	203.5 tok/s	951 ms	256K
Agentic Coding	A	Runs well	203.5 tok/s	1384 ms	256K
Reasoning	A	Runs well	203.5 tok/s	1124 ms	256K
RAG	A	Runs well	203.5 tok/s	1730 ms	256K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A73
Q3_K_S	3	15.0 GB	Low	A73
NVFP4	4	17.2 GB	Medium	A73
Q4_K_M	4	18.7 GB	Medium	A73
Q5_K_M	5	22.1 GB	High	A74
Q6_K	6	25.2 GB	High	A74
Q8_0	8	32.8 GB	Very High	A74
F16Best for your GPU	16	62.9 GB	Maximum	A77

Get started

Copy-paste commands to run Gemma 4 31B on your machine.

Run

ollama run gemma4:31b

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode
Qwen 3.5 397B A17B	397B	S	78.9 tok/s
Devstral 2 123B Instruct	123B	S	84.6 tok/s
Qwen 3.5 122B A10B	122B	S	234.8 tok/s
DeepSeek V4 Flash	284B	S	125.8 tok/s
Qwen 3.6 35B A3B	35B	S	742.2 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Gemma 4 31B?

Yes, AMD Instinct MI350X 288GB can run Gemma 4 31B with a A grade (Runs well). Expected decode speed: 203.5 tok/s.

How much VRAM does Gemma 4 31B need?

Gemma 4 31B (30.700000762939453B parameters) requires approximately 63.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 31B?

The recommended quantization for Gemma 4 31B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 31B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Gemma 4 31B achieves approximately 203.5 tokens per second decode speed with a time-to-first-token of 951ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Gemma 4 31B for coding?

For coding workloads, Gemma 4 31B on AMD Instinct MI350X 288GB receives a A grade with 203.5 tok/s and 256K context.

What context window can Gemma 4 31B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Gemma 4 31B can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Gemma 4 31B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gemma-4-31b-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: