Can Mixtral 8x22B run on H100 NVL 188GB?

YES — Runs Great

B68Good

Estimated from fit model

Mixtral 8x22B needs ~109.1 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~153 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) — 109.1 GB, 152.7 tok/s, Runs well

109.1 GB required188.0 GB available

58% VRAM used

Fit status

Runs well

Decode

152.7 tok/s

TTFT

1268 ms

Safe context

66K

Memory

109.1 GB / 188.0 GB

Memory breakdown

Weights86.0 GB

KV Cache3.4 GB

Runtime0.9 GB

Headroom18.8 GB

See how fast it feels

See how fast it feelsMixtral 8x22B 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: 152.7 tok/s decode · 1.3s TTFT (warm) · 382 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	B	Runs well	152.7 tok/s	692 ms	66K
Coding	B	Runs well	152.7 tok/s	1268 ms	66K
Agentic Coding	B	Runs well	152.7 tok/s	1845 ms	66K
Reasoning	B	Runs well	152.7 tok/s	1499 ms	66K
RAG	B	Runs well	152.7 tok/s	2306 ms	66K

Quantization options

How Mixtral 8x22B (141B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	55.0 GB	Low	B56
Q3_K_S	3	69.1 GB	Low	B57
NVFP4	4	79.0 GB	Medium	B59
Q4_K_M	4	86.0 GB	Medium	B59
Q5_K_M	5	101.5 GB	High	B61
Q6_K	6	115.6 GB	High	B61
Q8_0Best for your GPU	8	150.9 GB	Very High	B61
F16	16	289.0 GB	Maximum	F0

Get started

Copy-paste commands to run Mixtral 8x22B on your machine.

Run

ollama run mixtral:8x22b

Frequently asked questions

Can H100 NVL 188GB run Mixtral 8x22B?

Yes, H100 NVL 188GB can run Mixtral 8x22B with a B grade (Runs well). Expected decode speed: 152.7 tok/s.

How much VRAM does Mixtral 8x22B need?

Mixtral 8x22B (141B parameters) requires approximately 109.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Mixtral 8x22B?

The recommended quantization for Mixtral 8x22B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mixtral 8x22B run at on H100 NVL 188GB?

On H100 NVL 188GB, Mixtral 8x22B achieves approximately 152.7 tokens per second decode speed with a time-to-first-token of 1268ms using Q4_K_M quantization.

Can H100 NVL 188GB run Mixtral 8x22B for coding?

For coding workloads, Mixtral 8x22B on H100 NVL 188GB receives a B grade with 152.7 tok/s and 66K context.

What context window can Mixtral 8x22B use on H100 NVL 188GB?

On H100 NVL 188GB, Mixtral 8x22B can safely use up to 66K tokens of context. The model's official context limit is 66K, but available memory constrains the safe maximum.

See all results for H100 NVL 188GB See all hardware for Mixtral 8x22B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mixtral-8x22b-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: