Can GPT-OSS 20B run on Gaudi 3 128GB?

YES — Runs Great

S85Excellent

Estimated from fit model

GPT-OSS 20B needs ~29.0 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~497 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) — 29.0 GB, 497.2 tok/s, Runs well

29.0 GB required128.0 GB available

23% VRAM used

Fit status

Runs well

Decode

497.2 tok/s

TTFT

389 ms

Safe context

128K

Memory

29.0 GB / 128.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B on Gaudi 3 128GB
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: 497.2 tok/s decode · 389ms TTFT (warm) · 1243 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	497.2 tok/s	350 ms	128K
Coding	S	Runs well	497.2 tok/s	389 ms	128K
Agentic Coding	S	Runs well	497.2 tok/s	566 ms	128K
Reasoning	S	Runs well	497.2 tok/s	460 ms	128K
RAG	S	Runs well	497.2 tok/s	708 ms	128K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A77
Q3_K_S	3	10.3 GB	Low	A77
NVFP4	4	11.8 GB	Medium	A77
Q4_K_M	4	12.8 GB	Medium	A77
Q5_K_M	5	15.1 GB	High	A77
Q6_K	6	17.2 GB	High	A77
Q8_0	8	22.5 GB	Very High	A78
F16Best for your GPU	16	43.1 GB	Maximum	A81

Get started

Copy-paste commands to run GPT-OSS 20B on your machine.

Run

ollama run gpt-oss

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	37.5 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	391.6 tok/s
Qwen 3.5 27B	27B	S	169.8 tok/s
Qwen 3.6 27B	27B	S	105.9 tok/s
Qwen 3.5 122B A10B	122B	S	104.1 tok/s

Frequently asked questions

Can Gaudi 3 128GB run GPT-OSS 20B?

Yes, Gaudi 3 128GB can run GPT-OSS 20B with a S grade (Runs well). Expected decode speed: 497.2 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 29.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, GPT-OSS 20B achieves approximately 497.2 tokens per second decode speed with a time-to-first-token of 389ms using Q4_K_M quantization.

Can Gaudi 3 128GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on Gaudi 3 128GB receives a S grade with 497.2 tok/s and 128K context.

What context window can GPT-OSS 20B use on Gaudi 3 128GB?

On Gaudi 3 128GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if GPT-OSS 20B feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for GPT-OSS 20B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GB See all hardware for GPT-OSS 20B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gpt-oss-20b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

497.2 tok/s

350 ms

128K

Coding

Runs well

497.2 tok/s

389 ms

128K

Agentic Coding

Runs well

497.2 tok/s

566 ms

128K

Reasoning

Runs well

497.2 tok/s

460 ms

128K

RAG

Runs well

497.2 tok/s

708 ms

128K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A77
Q3_K_S	3	10.3 GB	Low	A77
NVFP4	4	11.8 GB	Medium	A77
Q4_K_M	4	12.8 GB	Medium	A77
Q5_K_M	5	15.1 GB	High	A77
Q6_K	6	17.2 GB	High	A77
Q8_0	8	22.5 GB	Very High	A78
F16Best for your GPU	16	43.1 GB	Maximum	A81

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

37.5 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

391.6 tok/s

Qwen 3.5 27B

27B

169.8 tok/s

Qwen 3.6 27B

27B

105.9 tok/s

Qwen 3.5 122B A10B

122B

104.1 tok/s

Frequently asked questions

Can Gaudi 3 128GB run GPT-OSS 20B?

Yes, Gaudi 3 128GB can run GPT-OSS 20B with a S grade (Runs well). Expected decode speed: 497.2 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 29.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, GPT-OSS 20B achieves approximately 497.2 tokens per second decode speed with a time-to-first-token of 389ms using Q4_K_M quantization.

Can Gaudi 3 128GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on Gaudi 3 128GB receives a S grade with 497.2 tok/s and 128K context.

What context window can GPT-OSS 20B use on Gaudi 3 128GB?

On Gaudi 3 128GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if GPT-OSS 20B feels slow on Gaudi 3 128GB?

Would CUDA be a better path than Gaudi 3 128GB for GPT-OSS 20B?