Can Leanstral 119B A6B run on Gaudi 3 128GB?

YES — Runs Great

S92Excellent

Estimated from fit model

Leanstral 119B A6B needs ~96.6 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~79 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 96.6 GB, 78.9 tok/s, Runs well

96.6 GB required128.0 GB available

75% VRAM used

Fit status

Runs well

Decode

78.9 tok/s

TTFT

2454 ms

Safe context

73K

Memory

96.6 GB / 128.0 GB

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsLeanstral 119B A6B 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: 78.9 tok/s decode · 2.5s TTFT (warm) · 197 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	S	Runs well	78.9 tok/s	1338 ms	73K
Coding	S	Runs well	78.9 tok/s	2454 ms	73K
Agentic Coding	S	Tight fit	78.9 tok/s	3569 ms	73K
Reasoning	S	Runs well	78.9 tok/s	2900 ms	73K
RAG	S	Tight fit	78.9 tok/s	4462 ms	73K

Inference speed

Leanstral 119B A6B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Leanstral 119B A6B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~17 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	17.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	11.9	Too big
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	11.3	Too big
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	8.8	Too big
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	7.4	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	6.7	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	5.8	Too big
RTX 5090 32GB	32 GB	Q4_K_M	5.5	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	5.1	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	3.7	Too big
RTX 4090 24GB	24 GB	Q4_K_M	3.5	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	3.2	Too big
RTX 3090 24GB	24 GB	Q4_K_M	3.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.8	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.6	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.4	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A80
Q3_K_S	3	58.3 GB	Low	A82
NVFP4	4	66.6 GB	Medium	A83
Q4_K_M	4	72.6 GB	Medium	A84
Q5_K_M	5	85.7 GB	High	A84
Q6_KBest for your GPU	6	97.6 GB	High	A84
Q8_0	8	127.3 GB	Very High	F0
F16	16	244.0 GB	Maximum	F0

Get started

Copy-paste commands to run Leanstral 119B A6B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Leanstral-2603" \
  --hf-file "Leanstral-2603-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	30 tok/s
Qwen 3.5 122B A10B	122B	S	79.1 tok/s
Pixtral Large 124B	124B	S	29.8 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Leanstral 119B A6B?

Yes, Gaudi 3 128GB can run Leanstral 119B A6B with a S grade (Runs well). Expected decode speed: 78.9 tok/s.

How much VRAM does Leanstral 119B A6B need?

Leanstral 119B A6B (119B parameters) requires approximately 96.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Leanstral 119B A6B?

The recommended quantization for Leanstral 119B A6B is Q4_K_M, which balances quality and memory efficiency.

What speed will Leanstral 119B A6B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Leanstral 119B A6B achieves approximately 78.9 tokens per second decode speed with a time-to-first-token of 2454ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Leanstral 119B A6B for coding?

For coding workloads, Leanstral 119B A6B on Gaudi 3 128GB receives a S grade with 78.9 tok/s and 73K context.

What context window can Leanstral 119B A6B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Leanstral 119B A6B can safely use up to 73K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Leanstral 119B A6B 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 Leanstral 119B A6B?

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 Leanstral 119B A6B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/leanstral-119b-a6b-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: