Can MPT-30B-Instruct run on NVIDIA H100 80GB?

YES — Runs Great

A77Great

Estimated from fit model

MPT-30B-Instruct needs ~54.2 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q5_K_M quantization, expect ~133 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

Q5_K_M (High quality) — 54.2 GB, 132.9 tok/s, Runs well

54.2 GB required80.0 GB available

68% VRAM used

Fit status

Runs well

Decode

132.9 tok/s

TTFT

1457 ms

Safe context

Memory

54.2 GB / 80.0 GB

Memory breakdown

Weights21.6 GB

KV Cache23.4 GB

Runtime1.2 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsMPT-30B-Instruct on NVIDIA H100 80GB
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: 132.9 tok/s decode · 1.5s TTFT (warm) · 332 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	132.9 tok/s	795 ms	8K
Coding	A	Runs well	132.9 tok/s	1457 ms	8K
Agentic Coding	A	Runs with offload	132.9 tok/s	2119 ms	8K
Reasoning	A	Runs well	132.9 tok/s	1722 ms	8K
RAG	A	Runs with offload	132.9 tok/s	2649 ms	8K

Quantization options

How MPT-30B-Instruct (30B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	B61
Q3_K_S	3	14.7 GB	Low	B62
NVFP4	4	16.8 GB	Medium	B62
Q4_K_M	4	18.3 GB	Medium	B62
Q5_K_M	5	21.6 GB	High	B63
Q6_K	6	24.6 GB	High	B63
Q8_0	8	32.1 GB	Very High	B65
F16Best for your GPU	16	61.5 GB	Maximum	B68

Get started

Copy-paste commands to run MPT-30B-Instruct on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mosaicml/mpt-30b-instruct" \
  --hf-file "mpt-30b-instruct-Q5_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your NVIDIA H100 80GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	A	28.9 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	425.5 tok/s
Qwen 3.5 122B A10B	122B	S	85.5 tok/s
Qwen 3.6 35B A3B	35B	S	357.6 tok/s
Qwen 3.5 35B A3B	35B	S	388.9 tok/s

Frequently asked questions

Can NVIDIA H100 80GB run MPT-30B-Instruct?

Yes, NVIDIA H100 80GB can run MPT-30B-Instruct with a A grade (Runs well). Expected decode speed: 132.9 tok/s.

How much VRAM does MPT-30B-Instruct need?

MPT-30B-Instruct (30B parameters) requires approximately 54.2 GB of memory with Q5_K_M quantization.

What is the best quantization for MPT-30B-Instruct?

The recommended quantization for MPT-30B-Instruct is Q5_K_M, which balances quality and memory efficiency.

What speed will MPT-30B-Instruct run at on NVIDIA H100 80GB?

On NVIDIA H100 80GB, MPT-30B-Instruct achieves approximately 132.9 tokens per second decode speed with a time-to-first-token of 1457ms using Q5_K_M quantization.

Can NVIDIA H100 80GB run MPT-30B-Instruct for coding?

For coding workloads, MPT-30B-Instruct on NVIDIA H100 80GB receives a A grade with 132.9 tok/s and 8K context.

What context window can MPT-30B-Instruct use on NVIDIA H100 80GB?

On NVIDIA H100 80GB, MPT-30B-Instruct can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for NVIDIA H100 80GB See all hardware for MPT-30B-Instruct

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mpt-30b-instruct-on-h100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: