Would CUDA be a better path than Gaudi 3 128GB for StableLM 2 12B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

Can StableLM 2 12B run on Gaudi 3 128GB?

Q: What should I upgrade first if StableLM 2 12B feels slow on Gaudi 3 128GB?

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.

YES — Runs Great

C47Usable

Estimated from fit model

StableLM 2 12B needs ~34.5 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q5_K_M quantization, expect ~168 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

Q5_K_M (High quality) — 34.5 GB, 168.0 tok/s, Runs well

34.5 GB required128.0 GB available

27% VRAM used

Fit status

Runs well

Decode

168.0 tok/s

TTFT

1152 ms

Safe context

Memory

34.5 GB / 128.0 GB

Memory breakdown

Weights8.6 GB

KV Cache12.2 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsStableLM 2 12B 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: 168.0 tok/s decode · 1.2s TTFT (warm) · 420 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	168.0 tok/s	629 ms	4K
Coding	C	Runs well	168.0 tok/s	1152 ms	4K
Agentic Coding	C	Runs well	168.0 tok/s	1676 ms	4K
Reasoning	C	Runs well	168.0 tok/s	1362 ms	4K
RAG	C	Runs well	168.0 tok/s	2095 ms	4K

Quantization options

How StableLM 2 12B (12B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	D38
Q3_K_S	3	5.9 GB	Low	D38
NVFP4	4

Get started

Copy-paste commands to run StableLM 2 12B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "stabilityai/stablelm-2-12b-chat" \
  --hf-file "stablelm-2-12b-chat-Q5_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can Gaudi 3 128GB run StableLM 2 12B?

Yes, Gaudi 3 128GB can run StableLM 2 12B with a C grade (Runs well). Expected decode speed: 168.0 tok/s.

How much VRAM does StableLM 2 12B need?

StableLM 2 12B (12B parameters) requires approximately 34.5 GB of memory with Q5_K_M quantization.

What is the best quantization for StableLM 2 12B?

The recommended quantization for StableLM 2 12B is Q5_K_M, which balances quality and memory efficiency.

What speed will StableLM 2 12B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, StableLM 2 12B achieves approximately 168.0 tokens per second decode speed with a time-to-first-token of 1152ms using Q5_K_M quantization.

Can Gaudi 3 128GB run StableLM 2 12B for coding?

For coding workloads, StableLM 2 12B on Gaudi 3 128GB receives a C grade with 168.0 tok/s and 4K context.

What context window can StableLM 2 12B use on Gaudi 3 128GB?

On Gaudi 3 128GB, StableLM 2 12B can safely use up to 4K tokens of context. The model's official context limit is 4K, but available memory constrains the safe maximum.

What should I upgrade first if StableLM 2 12B feels slow on Gaudi 3 128GB?

See all results for Gaudi 3 128GB See all hardware for StableLM 2 12B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/stablelm-2-12b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: