Can Mistral Small 4 119B run on NVIDIA H100 80GB?

BARELY — Tight on Memory

A84Great

○Estimated from fit model

Mistral Small 4 119B needs ~86.9 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~91 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 86.9 GB, 91.3 tok/s, Very compromised (needs ~5.7 GB host RAM)

86.9 GB required80.0 GB available

109% VRAM needed

6.9 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~5.7 GB host RAM)

Decode

91.3 tok/s

TTFT

2120 ms

Safe context

Memory

86.9 GB / 80.0 GB

Offload

10%

Memory breakdown

Weights72.6 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsMistral Small 4 119B on NVIDIA H100 80GB
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: 91.3 tok/s decode · 2.1s TTFT (warm) · 228 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 5.7 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	S	Runs with offload (needs ~3.6 GB host RAM)	96.2 tok/s	1098 ms	4K
Coding	A	Very compromised (needs ~5.7 GB host RAM)	91.3 tok/s	2120 ms	4K
Agentic Coding	A	Very compromised (needs ~9.6 GB host RAM)	82.7 tok/s	3404 ms	4K
Reasoning	A	Very compromised (needs ~5.7 GB host RAM)	91.3 tok/s	2505 ms	4K
RAG	A	Very compromised (needs ~9.6 GB host RAM)	82.7 tok/s	4255 ms	4K

Quantization options

How Mistral Small 4 119B (119B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	S88
Q3_K_SBest for your GPU	3	58.3 GB	Low	S88
NVFP4	4	66.6 GB	Medium	F0
Q4_K_M	4	72.6 GB	Medium	F0
Q5_K_M	5	85.7 GB	High	F0
Q6_K	6	97.6 GB	High	F0
Q8_0	8	127.3 GB	Very High	F0
F16	16	244.0 GB	Maximum	F0

Get started

Copy-paste commands to run Mistral Small 4 119B on your machine.

Run

lms load Mistral-Small-4-119B-2603 && lms server start

Your hardware

More models your NVIDIA H100 80GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	A	29 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	86 tok/s

Frequently asked questions

See all results for NVIDIA H100 80GB See all hardware for Mistral Small 4 119B

URL: https://willitrunai.com/can-run/mistral-small-4-119b-on-h100-80gb

⇱ Mistral Small 4 119B on NVIDIA H100 80GB? YES