Can Yi Coder 1.5B run on Gaudi 3 128GB?

YES — Runs Great

D39Poor

Estimated from fit model

Yi Coder 1.5B needs ~14.8 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~21 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

Q4_K_M (Medium quality) — 14.8 GB, 21.0 tok/s, Runs well

14.8 GB required128.0 GB available

12% VRAM used

Fit status

Runs well

Decode

21.0 tok/s

TTFT

9219 ms

Safe context

10.3M

Memory

14.8 GB / 128.0 GB

Memory breakdown

Weights0.9 GB

KV Cache0.2 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsYi Coder 1.5B on Gaudi 3 128GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 21.0 tok/s decode · 9.2s TTFT (warm) · 53 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	D	Runs well	21.0 tok/s	5029 ms	9.1M
Coding	D	Runs well	21.0 tok/s	9219 ms	10.3M
Agentic Coding	D	Runs well	21.0 tok/s	13410 ms	10.3M
Reasoning	D	Runs well	21.0 tok/s	10895 ms	10.3M
RAG	D	Runs well	21.0 tok/s	16762 ms	10.3M

Quantization options

How Yi Coder 1.5B (1.5B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.6 GB	Low	D38
Q3_K_S	3	0.7 GB	Low	D38
NVFP4	4	0.8 GB	Medium	D38
Q4_K_M	4	0.9 GB	Medium	D38
Q5_K_M	5	1.1 GB	High	D38
Q6_K	6	1.2 GB	High	D38
Q8_0	8	1.6 GB	Very High	D38
F16Best for your GPU	16	3.1 GB	Maximum	D38

Get started

Copy-paste commands to run Yi Coder 1.5B on your machine.

Run

lms load hf-lmstudio-community--yi-coder-1-5b-gguf && lms server start

Opciones de mejora

Hardware que ejecuta bien Yi Coder 1.5B

Mac Studio M3 Ultra 256GBOpción económica

256 GB Unified (+128)

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.21 tok/s decodificación

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$6,999 MSRP

Frequently asked questions

Can Gaudi 3 128GB run Yi Coder 1.5B?

Yes, Gaudi 3 128GB can run Yi Coder 1.5B with a D grade (Runs well). Expected decode speed: 21.0 tok/s.

How much VRAM does Yi Coder 1.5B need?

Yi Coder 1.5B (1.5B parameters) requires approximately 14.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Yi Coder 1.5B?

The recommended quantization for Yi Coder 1.5B is Q4_K_M, which balances quality and memory efficiency.

What speed will Yi Coder 1.5B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Yi Coder 1.5B achieves approximately 21.0 tokens per second decode speed with a time-to-first-token of 9219ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Yi Coder 1.5B for coding?

For coding workloads, Yi Coder 1.5B on Gaudi 3 128GB receives a D grade with 21.0 tok/s and 10.3M context.

What context window can Yi Coder 1.5B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Yi Coder 1.5B can safely use up to 10.3M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Yi Coder 1.5B 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.

Would CUDA be a better path than Gaudi 3 128GB for Yi Coder 1.5B?

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.

See all results for Gaudi 3 128GB See all hardware for Yi Coder 1.5B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--yi-coder-1-5b-gguf-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: