Can Gemma 4 31B run on AMD Instinct MI325X 256GB?

YES — Runs Great

A84Great

Estimated from fit model

Gemma 4 31B needs ~59.9 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~153 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) — 59.9 GB, 152.6 tok/s, Runs well

59.9 GB required256.0 GB available

23% VRAM used

Fit status

Runs well

Decode

152.6 tok/s

TTFT

1269 ms

Safe context

230K

Memory

59.9 GB / 256.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

See how fast it feelsGemma 4 31B 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: 152.6 tok/s decode · 1.3s TTFT (warm) · 382 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	152.6 tok/s	692 ms	230K
Coding	A	Runs well	152.6 tok/s	1269 ms	230K
Agentic Coding	A	Runs well	152.6 tok/s	1845 ms	230K
Reasoning	A	Runs well	152.6 tok/s	1499 ms	230K
RAG	A	Runs well	152.6 tok/s	2306 ms	230K

Inference speed

Gemma 4 31B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Gemma 4 31B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~26 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	25.5	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	25.5	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	23.7	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	19.7	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	18.7	Fits
RTX 5090 32GB	32 GB	Q4_K_M	15.0	Heavy offload
RTX 4090 24GB	24 GB	Q4_K_M	13.0	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	13.0	Heavy offload
RTX 3090 24GB	24 GB	Q4_K_M	11.1	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	10.2	Tight
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	9.3	Tight
RX 7900 XTX 24GB	24 GB	Q4_K_M	7.8	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	5.1	Too big
RTX 4070 12GB	12 GB	Q4_K_M	3.2	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 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	A74
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	A75
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 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
Qwen 3.6 35B A3B	35B	S	556.6 tok/s

Frequently asked questions

Can AMD Instinct MI325X 256GB run Gemma 4 31B?

Yes, AMD Instinct MI325X 256GB can run Gemma 4 31B with a A grade (Runs well). Expected decode speed: 152.6 tok/s.

How much VRAM does Gemma 4 31B need?

Gemma 4 31B (30.700000762939453B parameters) requires approximately 59.9 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 MI325X 256GB?

On AMD Instinct MI325X 256GB, Gemma 4 31B achieves approximately 152.6 tokens per second decode speed with a time-to-first-token of 1269ms using Q4_K_M quantization.

Can AMD Instinct MI325X 256GB run Gemma 4 31B for coding?

For coding workloads, Gemma 4 31B on AMD Instinct MI325X 256GB receives a A grade with 152.6 tok/s and 230K context.

What context window can Gemma 4 31B use on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, Gemma 4 31B can safely use up to 230K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI325X 256GB 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-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: