10 GB VRAM (+2)
C
Adds memory headroom for longer context windows and future model growth.43.1 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$219 MSRP
Can EXAONE 3.5 7.8B Instruct run on Intel Arc A750 8GB?
YES — Tight Fit
C51Usable
○Estimated from fit model
EXAONE 3.5 7.8B Instruct needs ~7.4 GB VRAM. Intel Arc A750 8GB has 8.0 GB. With Q4_K_M quantization, expect ~46 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: MediumStack: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 7.4 GB, 46.3 tok/s, Tight fit
7.4 GB required8.0 GB available
93% VRAM used
Fit status
Tight fit
Decode
46.3 tok/s
TTFT
4184 ms
Safe context
27K
Memory
7.4 GB / 8.0 GB
Memory breakdown
Weights4.8 GB
KV Cache0.9 GB
Runtime0.9 GB
Headroom0.8 GB
See how fast it feels
See how fast it feelsEXAONE 3.5 7.8B Instruct on Intel Arc A750 8GB
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: 46.3 tok/s decode · 4.2s TTFT (warm) · 116 tok/s prefill
What limits this setup
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 46.3 tok/s | 2282 ms | 27K |
| Coding | C | Tight fit | 46.3 tok/s | 4184 ms | 27K |
| Agentic Coding | C | Runs with offload (needs ~0.2 GB host RAM) | 32.2 tok/s | 8737 ms | 27K |
| Reasoning | C | Tight fit | 46.3 tok/s | 4945 ms | 27K |
| RAG | C | Runs with offload (needs ~0.2 GB host RAM) | 32.2 tok/s | 10922 ms | 27K |
Quantization options
How EXAONE 3.5 7.8B Instruct (7.800000190734863B params) fits at each quantization level on Intel Arc A750 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.0 GB | Low | C54 |
Q3_K_S | 3 | 3.8 GB | Low | C53 |
NVFP4 | 4 | 4.4 GB | Medium | C53 |
Q4_K_MBest for your GPU | 4 | 4.8 GB | Medium | C53 |
Q5_K_M | 5 | 5.6 GB | High | F0 |
Q6_K | 6 | 6.4 GB | High | F0 |
Q8_0 | 8 | 8.3 GB | Very High | F0 |
F16 | 16 | 16.0 GB | Maximum | F0 |
Get started
Copy-paste commands to run EXAONE 3.5 7.8B Instruct on your machine.
Run
lms load hf-lgai-exaone--exaone-3-5-7-8b-instruct-gguf && lms server startUpgrade options
Hardware that runs EXAONE 3.5 7.8B Instruct well
12 GB VRAM (+4)
C
Adds memory headroom for longer context windows and future model growth.46 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$249 MSRP
12 GB VRAM (+4)
C
Adds memory headroom for longer context windows and future model growth.39.5 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$499 MSRP