VOOZH about

URL: https://willitrunai.com/can-run/mpt-30b-instruct-on-gaudi-3-128gb

⇱ MPT-30B-Instruct on Gaudi 3 128GB? YES

Can MPT-30B-Instruct run on Gaudi 3 128GB?

YES — Runs Great

A72Great
○Estimated from fit model

MPT-30B-Instruct needs ~59.0 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q5_K_M quantization, expect ~122 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced
Share:

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) — 59.0 GB, 122.3 tok/s, Runs well
59.0 GB required128.0 GB available
46% VRAM used

Fit status

Runs well

Decode

122.3 tok/s

TTFT

1583 ms

Safe context

8K

Memory

59.0 GB / 128.0 GB

Memory breakdown

Weights21.6 GB
KV Cache23.4 GB
Runtime1.2 GB
Headroom12.8 GB

See how fast it feels

See how fast it feelsMPT-30B-Instruct on Gaudi 3 128GB
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: 122.3 tok/s decode · 1.6s TTFT (warm) · 306 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns well122.3 tok/s863 ms8K
CodingARuns well122.3 tok/s1583 ms8K
Agentic CodingARuns well122.3 tok/s2302 ms8K
ReasoningARuns well122.3 tok/s1871 ms8K
RAGARuns well122.3 tok/s2878 ms8K

Quantization options

How MPT-30B-Instruct (30B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
11.7 GB
LowB59
Q3_K_S
3
14.7 GB
LowB59
NVFP4
4
16.8 GB
MediumB59
Q4_K_M
4
18.3 GB
MediumB60
Q5_K_M
5
21.6 GB
HighB60
Q6_K
6
24.6 GB
HighB60
Q8_0
8
32.1 GB
Very HighB61
F16Best for your GPU
16
61.5 GB
MaximumB66

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 Gaudi 3 128GB can run

ModelParamsGradeDecodeCapabilities
👁 Mistral
Devstral 2 123B Instruct		123BS37.5 tok/s
👁 Alibaba
Qwen3-Coder 30B A3B Instruct		30.5BS391.6 tok/s
👁 Alibaba
Qwen 3.5 122B A10B		122BS104.1 tok/s
👁 Alibaba
Qwen 3.6 35B A3B		35BS329.1 tok/s
👁 Alibaba
Qwen 3.5 35B A3B		35BS357.9 tok/s

Frequently asked questions

See all results for Gaudi 3 128GBSee all hardware for MPT-30B-Instruct