VOOZH about

URL: https://willitrunai.com/can-run/hf-bartowski--aya-expanse-8b-gguf-on-m3-ultra-96gb

⇱ aya expanse 8b on Mac Studio M3 Ultra 96GB? YES

Can aya expanse 8b run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

C47Usable
○Estimated from fit model

aya expanse 8b needs ~17.1 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~112 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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

Q4_K_M (Medium quality) — 17.1 GB, 112.0 tok/s, Runs well
17.1 GB required69.1 GB available
25% VRAM used

Fit status

Runs well

Decode

112.0 tok/s

TTFT

1729 ms

Safe context

904K

Memory

17.1 GB / 69.1 GB

Memory breakdown

Weights4.9 GB
KV Cache0.9 GB
Runtime0.9 GB
Headroom10.4 GB

See how fast it feels

See how fast it feelsaya expanse 8b on Mac Studio M3 Ultra 96GB
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: 112.0 tok/s decode · 1.7s TTFT (warm) · 280 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well112.0 tok/s943 ms904K
CodingCRuns well112.0 tok/s1729 ms904K
Agentic CodingCRuns well112.0 tok/s2514 ms904K
ReasoningCRuns well112.0 tok/s2043 ms904K
RAGCRuns well112.0 tok/s3143 ms904K

Quantization options

How aya expanse 8b (8B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
LowD40
Q3_K_S
3
3.9 GB
LowD40
NVFP4
4
4.5 GB
MediumD40
Q4_K_M
4
4.9 GB
MediumC40
Q5_K_M
5
5.8 GB
HighC40
Q6_K
6
6.6 GB
HighC40
Q8_0
8
8.6 GB
Very HighC40
F16Best for your GPU
16
16.4 GB
MaximumC42

Get started

Copy-paste commands to run aya expanse 8b on your machine.

Run

lms load hf-bartowski--aya-expanse-8b-gguf && lms server start

Frequently asked questions

See all results for Mac Studio M3 Ultra 96GBSee all hardware for aya expanse 8b