Can Llama 4 Maverick 17B 128E run on B100 192GB?

YES — With Q3_K_S

A77Great

Estimated from fit model

Llama 4 Maverick 17B 128E needs ~219.0 GB VRAM. B100 192GB has 192.0 GB. With Q3_K_S quantization, expect ~71 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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.

Llama 4 Maverick 17B 128E at Q4_K_M needs 267.0 GB — too much for B100 192GB (192.0 GB). Runs at Q3_K_S (219.0 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 267.0 GB, exceeds 192.0 GB available

267.0 GB required192.0 GB available

139% VRAM needed

75.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

44.1 tok/s

TTFT

4392 ms

Safe context

Memory

267.0 GB / 192.0 GB

Offload

30%

Memory breakdown

Weights244.0 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom19.2 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsLlama 4 Maverick 17B 128E on B100 192GB
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: 44.1 tok/s decode · 4.4s TTFT (warm) · 110 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 24.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	44.5 tok/s	2374 ms	4K
Coding	F	Too heavy	44.1 tok/s	4392 ms	4K
Agentic Coding	F	Too heavy	43.3 tok/s	6505 ms	4K
Reasoning	F	Too heavy	44.1 tok/s	5191 ms	4K
RAG	F	Too heavy	43.3 tok/s	8131 ms	4K

Quantization options

How Llama 4 Maverick 17B 128E (400B params) fits at each quantization level on B100 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	156.0 GB	Low	F0
Q3_K_S	3	196.0 GB	Low	F0
NVFP4	4	224.0 GB	Medium	F0
Q4_K_M	4	244.0 GB	Medium	F0
Q5_K_M	5	288.0 GB	High	F0
Q6_K	6	328.0 GB	High	F0
Q8_0	8	428.0 GB	Very High	F0
F16	16	820.0 GB	Maximum	F0

Get started

Copy-paste commands to run Llama 4 Maverick 17B 128E on your machine.

Run

lms load Llama-4-Maverick-17B-128E-Instruct && lms server start

Upgrade options

Hardware that runs Llama 4 Maverick 17B 128E well

AMD Instinct MI350X 288GBBudget pick

288 GB VRAM (+96)

Makes the model fit on the accelerator instead of staying completely out of reach.77.4 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$8,000 MSRP

AMD Instinct MI325X 256GBBest value

256 GB VRAM (+64)

Makes the model fit on the accelerator instead of staying completely out of reach.37.9 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Adds memory headroom for longer context windows and future model growth.

~$20,000 MSRP

Frequently asked questions

Can B100 192GB run Llama 4 Maverick 17B 128E?

Yes, B100 192GB can run Llama 4 Maverick 17B 128E at Q3_K_S quantization (Very compromised (needs ~24.2 GB host RAM)). The recommended Q4_K_M requires 267.0 GB which exceeds available memory, but at Q3_K_S it needs only 219.0 GB. Expected decode speed: 70.8 tok/s.

How much VRAM does Llama 4 Maverick 17B 128E need?

Llama 4 Maverick 17B 128E (400B parameters) requires approximately 267.0 GB at Q4_K_M quantization. On B100 192GB, it fits at Q3_K_S using 219.0 GB.

What is the best quantization for Llama 4 Maverick 17B 128E?

The recommended quantization is Q4_K_M, but on B100 192GB the best fitting quantization is Q3_K_S, which uses 219.0 GB.

What speed will Llama 4 Maverick 17B 128E run at on B100 192GB?

On B100 192GB, Llama 4 Maverick 17B 128E achieves approximately 70.8 tokens per second decode speed with a time-to-first-token of 2736ms using Q3_K_S quantization.

Can B100 192GB run Llama 4 Maverick 17B 128E for coding?

For coding workloads, Llama 4 Maverick 17B 128E on B100 192GB receives a F grade with 44.1 tok/s and 4K context.

What context window can Llama 4 Maverick 17B 128E use on B100 192GB?

On B100 192GB, Llama 4 Maverick 17B 128E can safely use up to 4K tokens of context at Q3_K_S quantization. The model's official context limit is 1.0M, but available memory constrains the safe maximum.

What should I upgrade first if Llama 4 Maverick 17B 128E feels slow on B100 192GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for B100 192GB See all hardware for Llama 4 Maverick 17B 128E

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/llama-4-maverick-17b-128e-on-b100-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 24.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Too heavy

44.5 tok/s

2374 ms

Coding

Too heavy

44.1 tok/s

4392 ms

Agentic Coding

Too heavy

43.3 tok/s

6505 ms

Reasoning

Too heavy

44.1 tok/s

5191 ms

RAG

Too heavy

43.3 tok/s

8131 ms

Quantization options

How Llama 4 Maverick 17B 128E (400B params) fits at each quantization level on B100 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	156.0 GB	Low	F0
Q3_K_S	3	196.0 GB	Low	F0
NVFP4	4	224.0 GB	Medium	F0
Q4_K_M	4	244.0 GB	Medium	F0
Q5_K_M	5	288.0 GB	High	F0
Q6_K	6	328.0 GB	High	F0
Q8_0	8	428.0 GB	Very High	F0
F16	16	820.0 GB	Maximum	F0

Frequently asked questions

Can B100 192GB run Llama 4 Maverick 17B 128E?

How much VRAM does Llama 4 Maverick 17B 128E need?

Llama 4 Maverick 17B 128E (400B parameters) requires approximately 267.0 GB at Q4_K_M quantization. On B100 192GB, it fits at Q3_K_S using 219.0 GB.

What is the best quantization for Llama 4 Maverick 17B 128E?

The recommended quantization is Q4_K_M, but on B100 192GB the best fitting quantization is Q3_K_S, which uses 219.0 GB.

What speed will Llama 4 Maverick 17B 128E run at on B100 192GB?

On B100 192GB, Llama 4 Maverick 17B 128E achieves approximately 70.8 tokens per second decode speed with a time-to-first-token of 2736ms using Q3_K_S quantization.

Can B100 192GB run Llama 4 Maverick 17B 128E for coding?

For coding workloads, Llama 4 Maverick 17B 128E on B100 192GB receives a F grade with 44.1 tok/s and 4K context.

What context window can Llama 4 Maverick 17B 128E use on B100 192GB?

What should I upgrade first if Llama 4 Maverick 17B 128E feels slow on B100 192GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.