Can Gemma 4 31B run on AMD Instinct MI300X 192GB?

YES — Runs Great

A85Great

Estimated from fit model

Gemma 4 31B needs ~53.5 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~144 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) — 53.5 GB, 144.0 tok/s, Runs well

53.5 GB required192.0 GB available

28% VRAM used

Fit status

Runs well

Decode

144.0 tok/s

TTFT

1344 ms

Safe context

167K

Memory

53.5 GB / 192.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime0.9 GB

Headroom19.2 GB

See how fast it feels

See how fast it feelsGemma 4 31B on AMD Instinct MI300X 192GB
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: 144.0 tok/s decode · 1.3s TTFT (warm) · 360 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	144.0 tok/s	733 ms	167K
Coding	A	Runs well	144.0 tok/s	1344 ms	167K
Agentic Coding	S	Runs well	144.0 tok/s	1955 ms	167K
Reasoning	A	Runs well	144.0 tok/s	1588 ms	167K
RAG	S	Runs well	144.0 tok/s	2444 ms	167K

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 MI300X 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A74
Q3_K_S	3	15.0 GB	Low	A74
NVFP4	4	17.2 GB	Medium	A74
Q4_K_M	4	18.7 GB	Medium	A74
Q5_K_M	5	22.1 GB	High	A75
Q6_K	6	25.2 GB	High	A75
Q8_0	8	32.8 GB	Very High	A76
F16Best for your GPU	16	62.9 GB	Maximum	A79

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 MI300X 192GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	59.9 tok/s
Qwen 3.5 122B A10B	122B	S	166.2 tok/s
DeepSeek V4 Flash	284B	S	89.1 tok/s
Qwen 3.6 35B A3B	35B	S	525.4 tok/s
Qwen 3.5 35B A3B	35B	S	571.3 tok/s

Frequently asked questions

Can AMD Instinct MI300X 192GB run Gemma 4 31B?

Yes, AMD Instinct MI300X 192GB can run Gemma 4 31B with a A grade (Runs well). Expected decode speed: 144.0 tok/s.

How much VRAM does Gemma 4 31B need?

Gemma 4 31B (30.700000762939453B parameters) requires approximately 53.5 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 MI300X 192GB?

On AMD Instinct MI300X 192GB, Gemma 4 31B achieves approximately 144.0 tokens per second decode speed with a time-to-first-token of 1344ms using Q4_K_M quantization.

Can AMD Instinct MI300X 192GB run Gemma 4 31B for coding?

For coding workloads, Gemma 4 31B on AMD Instinct MI300X 192GB receives a A grade with 144.0 tok/s and 167K context.

What context window can Gemma 4 31B use on AMD Instinct MI300X 192GB?

On AMD Instinct MI300X 192GB, Gemma 4 31B can safely use up to 167K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI300X 192GB 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-mi300x-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: