Can Laguna S 2.1 run on NVIDIA H200 141GB?

YES — Runs Great

S91Excellent

Estimated from fit model

Laguna S 2.1 needs ~89.7 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~159 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) — 87.5 GB, 171.8 tok/s, Runs well

87.5 GB required141.0 GB available

62% VRAM used

Fit status

Runs well

Decode

171.8 tok/s

TTFT

1127 ms

Safe context

1.0M

Memory

87.5 GB / 141.0 GB

Memory breakdown

Weights71.7 GB

KV Cache0.7 GB

Runtime0.9 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsLaguna S 2.1 on NVIDIA H200 141GB
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: 171.8 tok/s decode · 1.1s TTFT (warm) · 430 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	S	Runs well	158.6 tok/s	666 ms	296K
Coding	S	Runs well	158.6 tok/s	1221 ms	296K
Agentic Coding	S	Runs well	158.6 tok/s	1776 ms	296K
Reasoning	S	Runs well	158.6 tok/s	1443 ms	296K
RAG	S	Runs well	158.6 tok/s	2220 ms	296K

Inference speed

Laguna S 2.1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Laguna S 2.1 at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~37 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?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	36.8	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	30.6	Tight
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	29.1	Tight
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	22.7	Tight
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	13.5	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	11.2	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	9.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	7.8	Too big
RTX 5090 32GB	32 GB	Q4_K_M	7.7	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	7.7	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	7.2	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	6.8	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	6.2	Too big
RTX 4090 24GB	24 GB	Q4_K_M	4.9	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	4.4	Too big
RTX 3090 24GB	24 GB	Q4_K_M	4.2	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	3.9	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.4	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 Laguna S 2.1 (117.5999984741211B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	16.9 GB	Very Low	A74
Q2_0_G128	1.71	31.4 GB	Low	A76
Q2_K	2	45.9 GB	Low	A79
Q3_K_S	3	57.6 GB	Low	A80
NVFP4	4	65.9 GB	Medium	A82
Q4_K_M	4	71.7 GB	Medium	A83
Q5_K_M	5	84.7 GB	High	A83
Q6_KBest for your GPU	6	96.4 GB	High	A83
Q8_0	8	125.8 GB	Very High	F0
F16	16	241.1 GB	Maximum	F0

Get started

Copy-paste commands to run Laguna S 2.1 on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "poolside/Laguna-S-2.1" \
  --hf-file "Laguna-S-2.1-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your NVIDIA H200 141GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	58.4 tok/s
Qwen 3.5 122B A10B	122B	S	162.1 tok/s
Solar Open 2 250B	250.3B	A	52.5 tok/s
Pixtral Large 124B	124B	S	58 tok/s

Frequently asked questions

Can NVIDIA H200 141GB run Laguna S 2.1?

Yes, NVIDIA H200 141GB can run Laguna S 2.1 with a S grade (Runs well). Expected decode speed: 158.6 tok/s.

How much VRAM does Laguna S 2.1 need?

Laguna S 2.1 (117.5999984741211B parameters) requires approximately 89.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Laguna S 2.1?

The recommended quantization for Laguna S 2.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Laguna S 2.1 run at on NVIDIA H200 141GB?

On NVIDIA H200 141GB, Laguna S 2.1 achieves approximately 158.6 tokens per second decode speed with a time-to-first-token of 1221ms using Q4_K_M quantization.

Can NVIDIA H200 141GB run Laguna S 2.1 for coding?

For coding workloads, Laguna S 2.1 on NVIDIA H200 141GB receives a S grade with 158.6 tok/s and 296K context.

What context window can Laguna S 2.1 use on NVIDIA H200 141GB?

On NVIDIA H200 141GB, Laguna S 2.1 can safely use up to 296K tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.

See all results for NVIDIA H200 141GB See all hardware for Laguna S 2.1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/laguna-s-2.1-on-h200-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: