Can Dolphin 2.9 8B run on Intel Arc A730M 12GB?

YES — Runs Great

C55Usable

○Estimated from fit model

Dolphin 2.9 8B needs ~8.9 GB VRAM. Intel Arc A730M 12GB has 12.0 GB. With Q4_K_M quantization, expect ~36 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: 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) — 8.9 GB, 36.3 tok/s, Runs well

8.9 GB required12.0 GB available

74% VRAM used

Fit status

Runs well

Decode

36.3 tok/s

TTFT

5338 ms

Safe context

33K

Memory

8.9 GB / 12.0 GB

Memory breakdown

Weights4.9 GB

KV Cache2.0 GB

Runtime0.9 GB

Headroom1.2 GB

See how fast it feels

See how fast it feelsDolphin 2.9 8B on Intel Arc A730M 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: 36.3 tok/s decode · 5.3s TTFT (warm) · 91 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	36.3 tok/s	2912 ms	33K
Coding	C	Runs well	36.3 tok/s	5338 ms	33K
Agentic Coding	C	Tight fit	36.3 tok/s	7764 ms	33K
Reasoning	C	Runs well	36.3 tok/s	6309 ms	33K
RAG	C	Tight fit	36.3 tok/s	9706 ms	33K

Quantization options

How Dolphin 2.9 8B (8B params) fits at each quantization level on Intel Arc A730M 12GB (12.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.1 GB	Low	C50
Q3_K_S	3	3.9 GB	Low	C51
NVFP4	4	4.5 GB	Medium	C52
Q4_K_M	4	4.9 GB	Medium	C52
Q5_K_M	5	5.8 GB	High	C53
Q6_K	6	6.6 GB	High	C53
Q8_0Best for your GPU	8	8.6 GB	Very High	C52
F16	16	16.4 GB	Maximum	F0