Can aya expanse 32b heretic MPOA i1 run on Gaudi 3 128GB?

YES — Runs Great

C48Usable

○Estimated from fit model

aya expanse 32b heretic MPOA i1 needs ~37.0 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~133 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) — 37.0 GB, 132.7 tok/s, Runs well

37.0 GB required128.0 GB available

29% VRAM used

Fit status

Runs well

Decode

132.7 tok/s

TTFT

1459 ms

Safe context

404K

Memory

37.0 GB / 128.0 GB

Memory breakdown

Weights19.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsaya expanse 32b heretic MPOA i1 on Gaudi 3 128GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
 - Full privacy: your prompts never leave your machine
 - No per-token cost or rate limits
 - Works offline once the model is downloaded
 - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

 Model size Q4 (4-bit) Q8 (8-bit) FP16
 7B params ~4.3 GB ~7.5 GB ~14 GB
 13B params ~7.9 GB ~13.9 GB ~26 GB
 70B params ~42.7 GB ~74.9 GB ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 132.7 tok/s decode · 1.5s TTFT (warm) · 332 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	132.7 tok/s	796 ms	404K
Coding	C	Runs well	132.7 tok/s	1459 ms	404K
Agentic Coding	C	Runs well	132.7 tok/s	2122 ms	404K
Reasoning	C	Runs well	132.7 tok/s	1724 ms	404K
RAG	C	Runs well	132.7 tok/s	2653 ms	404K

Quantization options

How aya expanse 32b heretic MPOA i1 (32B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	D38
Q3_K_S	3	15.7 GB	Low	D38
NVFP4	4

Get started

Copy-paste commands to run aya expanse 32b heretic MPOA i1 on your machine.

Run

lms load hf-mradermacher--aya-expanse-32b-heretic-mpoa-i1-gguf && lms server start

Frequently asked questions

See all results for Gaudi 3 128GB See all hardware for aya expanse 32b heretic MPOA i1

URL: https://willitrunai.com/can-run/hf-mradermacher--aya-expanse-32b-heretic-mpoa-i1-gguf-on-gaudi-3-128gb

⇱