VOOZH about

URL: https://willitrunai.com/can-run/hf-lmstudio-community--exaone-3-5-7-8b-instruct-gguf-on-arc-pro-a60-12gb

⇱ EXAONE 3.5 7.8B Instruct on Intel Arc Pro A60 12GB? YES

Can EXAONE 3.5 7.8B Instruct run on Intel Arc Pro A60 12GB?

YES — Runs Great

C53Usable
○Estimated from fit model

EXAONE 3.5 7.8B Instruct needs ~7.8 GB VRAM. Intel Arc Pro A60 12GB has 12.0 GB. With Q4_K_M quantization, expect ~40 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: 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) — 7.8 GB, 39.5 tok/s, Runs well
7.8 GB required12.0 GB available
65% VRAM used

Fit status

Runs well

Decode

39.5 tok/s

TTFT

4896 ms

Safe context

90K

Memory

7.8 GB / 12.0 GB

Memory breakdown

Weights4.8 GB
KV Cache0.9 GB
Runtime0.9 GB
Headroom1.2 GB

See how fast it feels

See how fast it feelsEXAONE 3.5 7.8B Instruct on Intel Arc Pro A60 12GB
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: 39.5 tok/s decode · 4.9s TTFT (warm) · 99 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
ChatCRuns well39.5 tok/s2670 ms90K
CodingCRuns well39.5 tok/s4896 ms90K
Agentic CodingCRuns well39.5 tok/s7121 ms90K
ReasoningCRuns well39.5 tok/s5786 ms90K
RAGCRuns well39.5 tok/s8901 ms90K

Quantization options

How EXAONE 3.5 7.8B Instruct (7.800000190734863B params) fits at each quantization level on Intel Arc Pro A60 12GB (12.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.0 GB
LowC49
Q3_K_S
3
3.8 GB
LowC50
NVFP4
4
4.4 GB
MediumC51
Q4_K_M
4
4.8 GB
MediumC51
Q5_K_M
5
5.6 GB
HighC52
Q6_K
6
6.4 GB
HighC52
Q8_0Best for your GPU
8
8.3 GB
Very HighC51
F16
16
16.0 GB
MaximumF0

Get started

Copy-paste commands to run EXAONE 3.5 7.8B Instruct on your machine.

Run

lms load hf-lmstudio-community--exaone-3-5-7-8b-instruct-gguf && lms server start

Frequently asked questions

See all results for Intel Arc Pro A60 12GBSee all hardware for EXAONE 3.5 7.8B Instruct