Can Llama 4 Scout 17B 16E run on Gaudi 3 128GB?

YES — Runs Great

A84Great

Estimated from fit model

Llama 4 Scout 17B 16E needs ~83.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~99 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) — 83.1 GB, 99.0 tok/s, Runs well

83.1 GB required128.0 GB available

65% VRAM used

Fit status

Runs well

Decode

99.0 tok/s

TTFT

1955 ms

Safe context

261K

Memory

83.1 GB / 128.0 GB

Memory breakdown

Weights66.5 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsLlama 4 Scout 17B 16E on Gaudi 3 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
  - Speed = 60 mph (miles per hour)
  - Time  = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
  Distance = 60 mph x 2.5 h
           = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
  - First half: 1.25 hours at 60 mph = 75 miles
  - Stop: 20 minutes (no distance)
  - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 99.0 tok/s decode · 2.0s TTFT (warm) · 248 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	A	Runs well	99.0 tok/s	1066 ms	261K
Coding	A	Runs well	99.0 tok/s	1955 ms	261K
Agentic Coding	A	Runs well	99.0 tok/s	2843 ms	261K
Reasoning	A	Runs well	99.0 tok/s	2310 ms	261K
RAG	A	Runs well	99.0 tok/s	3554 ms	261K

Quantization options

How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	42.5 GB	Low	A71
Q3_K_S	3	53.4 GB	Low	A73
NVFP4	4	61.0 GB	Medium	A74
Q4_K_M	4	66.5 GB	Medium	A75
Q5_K_M	5	78.5 GB	High	A76
Q6_KBest for your GPU	6	89.4 GB	High	A76
Q8_0	8	116.6 GB	Very High	F0
F16	16	223.5 GB	Maximum	F0

Get started

Copy-paste commands to run Llama 4 Scout 17B 16E on your machine.

Run

lms load Llama-4-Scout-17B-16E-Instruct && lms server start

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	37.5 tok/s
Qwen 3.5 122B A10B	122B	S	104.1 tok/s
Mistral Small 4 119B	119B	S	112.9 tok/s
GPT-OSS 120B	117B	S	39.5 tok/s
Command A 111B	111B	S	41.8 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Llama 4 Scout 17B 16E?

Yes, Gaudi 3 128GB can run Llama 4 Scout 17B 16E with a A grade (Runs well). Expected decode speed: 99.0 tok/s.

How much VRAM does Llama 4 Scout 17B 16E need?

Llama 4 Scout 17B 16E (109B parameters) requires approximately 83.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Llama 4 Scout 17B 16E?

The recommended quantization for Llama 4 Scout 17B 16E is Q4_K_M, which balances quality and memory efficiency.

What speed will Llama 4 Scout 17B 16E run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Llama 4 Scout 17B 16E achieves approximately 99.0 tokens per second decode speed with a time-to-first-token of 1955ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Llama 4 Scout 17B 16E for coding?

For coding workloads, Llama 4 Scout 17B 16E on Gaudi 3 128GB receives a A grade with 99.0 tok/s and 261K context.

What context window can Llama 4 Scout 17B 16E use on Gaudi 3 128GB?

On Gaudi 3 128GB, Llama 4 Scout 17B 16E can safely use up to 261K tokens of context. The model's official context limit is 10.5M, but available memory constrains the safe maximum.

What should I upgrade first if Llama 4 Scout 17B 16E 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 Llama 4 Scout 17B 16E?

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 Llama 4 Scout 17B 16E

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/llama-4-scout-17b-16e-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: