Can Llama 4 Scout 17B 16E run on H100 NVL 188GB?

YES — Runs Great

A80Great

Estimated from fit model

Llama 4 Scout 17B 16E needs ~89.4 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~242 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 89.4 GB, 241.6 tok/s, Runs well

89.4 GB required188.0 GB available

48% VRAM used

Fit status

Runs well

Decode

241.6 tok/s

TTFT

801 ms

Safe context

554K

Memory

89.4 GB / 188.0 GB

Memory breakdown

Weights66.5 GB

KV Cache2.9 GB

Runtime1.2 GB

Headroom18.8 GB

See how fast it feels

See how fast it feelsLlama 4 Scout 17B 16E on H100 NVL 188GB
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: 241.6 tok/s decode · 801ms TTFT (warm) · 604 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	241.6 tok/s	437 ms	554K
Coding	A	Runs well	241.6 tok/s	801 ms	554K
Agentic Coding	A	Runs well	241.6 tok/s	1166 ms	554K
Reasoning	A	Runs well	241.6 tok/s	947 ms	554K
RAG	A	Runs well	241.6 tok/s	1457 ms	554K

Quantization options

How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	42.5 GB	Low	B68
Q3_K_S	3	53.4 GB	Low	B70
NVFP4	4	61.0 GB	Medium	A71
Q4_K_M	4	66.5 GB	Medium	A71
Q5_K_M	5	78.5 GB	High	A73
Q6_K	6	89.4 GB	High	A74
Q8_0Best for your GPU	8	116.6 GB	Very High	A76
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 H100 NVL 188GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	91.6 tok/s
Qwen 3.5 122B A10B	122B	S	254 tok/s
DeepSeek V4 Flash	284B	S	136.1 tok/s
Mistral Small 4 119B	119B	S	275.4 tok/s
GPT-OSS 120B	117B	S	96.3 tok/s

Frequently asked questions

Can H100 NVL 188GB run Llama 4 Scout 17B 16E?

Yes, H100 NVL 188GB can run Llama 4 Scout 17B 16E with a A grade (Runs well). Expected decode speed: 241.6 tok/s.

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

Llama 4 Scout 17B 16E (109B parameters) requires approximately 89.4 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 H100 NVL 188GB?

On H100 NVL 188GB, Llama 4 Scout 17B 16E achieves approximately 241.6 tokens per second decode speed with a time-to-first-token of 801ms using Q4_K_M quantization.

Can H100 NVL 188GB run Llama 4 Scout 17B 16E for coding?

For coding workloads, Llama 4 Scout 17B 16E on H100 NVL 188GB receives a A grade with 241.6 tok/s and 554K context.

What context window can Llama 4 Scout 17B 16E use on H100 NVL 188GB?

On H100 NVL 188GB, Llama 4 Scout 17B 16E can safely use up to 554K tokens of context. The model's official context limit is 10.5M, but available memory constrains the safe maximum.

See all results for H100 NVL 188GB 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-h100-nvl-188gb" 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

241.6 tok/s

437 ms

554K

Coding

Runs well

241.6 tok/s

801 ms

554K

Agentic Coding

Runs well

241.6 tok/s

1166 ms

554K

Reasoning

Runs well

241.6 tok/s

947 ms

554K

RAG

Runs well

241.6 tok/s

1457 ms

554K

Quantization options

How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	42.5 GB	Low	B68
Q3_K_S	3	53.4 GB	Low	B70
NVFP4	4	61.0 GB	Medium	A71
Q4_K_M	4	66.5 GB	Medium	A71
Q5_K_M	5	78.5 GB	High	A73
Q6_K	6	89.4 GB	High	A74
Q8_0Best for your GPU	8	116.6 GB	Very High	A76
F16	16	223.5 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

91.6 tok/s

Qwen 3.5 122B A10B

122B

254 tok/s

DeepSeek V4 Flash

284B

136.1 tok/s

Mistral Small 4 119B

119B

275.4 tok/s

GPT-OSS 120B

117B

96.3 tok/s

Frequently asked questions

Can H100 NVL 188GB run Llama 4 Scout 17B 16E?

Yes, H100 NVL 188GB can run Llama 4 Scout 17B 16E with a A grade (Runs well). Expected decode speed: 241.6 tok/s.

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

Llama 4 Scout 17B 16E (109B parameters) requires approximately 89.4 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 H100 NVL 188GB?

On H100 NVL 188GB, Llama 4 Scout 17B 16E achieves approximately 241.6 tokens per second decode speed with a time-to-first-token of 801ms using Q4_K_M quantization.

Can H100 NVL 188GB run Llama 4 Scout 17B 16E for coding?

For coding workloads, Llama 4 Scout 17B 16E on H100 NVL 188GB receives a A grade with 241.6 tok/s and 554K context.

What context window can Llama 4 Scout 17B 16E use on H100 NVL 188GB?

On H100 NVL 188GB, Llama 4 Scout 17B 16E can safely use up to 554K tokens of context. The model's official context limit is 10.5M, but available memory constrains the safe maximum.