Can Leanstral 119B A6B run on NVIDIA GH200 96GB?

YES — With NVFP4

S89Excellent

Estimated from fit model

Leanstral 119B A6B needs ~87.4 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With NVFP4 quantization, expect ~81 tok/s.

Runtime: vLLMCapacity: TightBandwidth: 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.

Leanstral 119B A6B at Q4_K_M needs 93.4 GB — too much for NVIDIA GH200 96GB (96.0 GB). Runs at NVFP4 (87.4 GB) with medium quality. 3 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 93.4 GB, exceeds 96.0 GB available

93.4 GB required96.0 GB available

97% VRAM used

Fit status

Too heavy

Decode

71.1 tok/s

TTFT

2724 ms

Safe context

21K

Memory

93.4 GB / 96.0 GB

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom9.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsLeanstral 119B A6B on NVIDIA GH200 96GB
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: 71.1 tok/s decode · 2.7s TTFT (warm) · 178 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	71.1 tok/s	1486 ms	21K
Coding	F	Too heavy	71.1 tok/s	2724 ms	21K
Agentic Coding	F	Too heavy	54.7 tok/s	5149 ms	21K
Reasoning	F	Too heavy	71.1 tok/s	3220 ms	21K
RAG	F	Too heavy	54.7 tok/s	6436 ms	21K

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 NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A83
Q3_K_S	3	58.3 GB	Low	A84
NVFP4	4	66.6 GB	Medium	A84
Q4_K_MBest for your GPU	4	72.6 GB	Medium	A84
Q5_K_M	5	85.7 GB	High	F0
Q6_K	6	97.6 GB	High	F0
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

Upgrade-Optionen

Hardware, die Leanstral 119B A6B gut ausführt

NVIDIA H200 141GBGünstige Wahl

141 GB VRAM (+45)4800 GB/s (+800)

Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Adds memory headroom for longer context windows and future model growth.

ca. $30,000 MSRP

NVIDIA H200 PCIe 141GBBestes Preis-Leistungs-Verhältnis

141 GB VRAM (+45)4800 GB/s (+800)

Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Adds memory headroom for longer context windows and future model growth.

ca. $30,000 MSRP

NVIDIA B200 180GBNVIDIA-Upgrade

180 GB VRAM (+84)8000 GB/s (+4000)

Makes the model fit on the accelerator instead of staying completely out of reach.204.7 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 188%.

ca. $30,000 MSRP

Frequently asked questions

Can NVIDIA GH200 96GB run Leanstral 119B A6B?

Yes, NVIDIA GH200 96GB can run Leanstral 119B A6B at NVFP4 quantization (Tight fit). The recommended Q4_K_M requires 93.4 GB which exceeds available memory, but at NVFP4 it needs only 87.4 GB. Expected decode speed: 81.3 tok/s.

How much VRAM does Leanstral 119B A6B need?

Leanstral 119B A6B (119B parameters) requires approximately 93.4 GB at Q4_K_M quantization. On NVIDIA GH200 96GB, it fits at NVFP4 using 87.4 GB.

What is the best quantization for Leanstral 119B A6B?

The recommended quantization is Q4_K_M, but on NVIDIA GH200 96GB the best fitting quantization is NVFP4, which uses 87.4 GB.

What speed will Leanstral 119B A6B run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Leanstral 119B A6B achieves approximately 81.3 tokens per second decode speed with a time-to-first-token of 2382ms using NVFP4 quantization.

Can NVIDIA GH200 96GB run Leanstral 119B A6B for coding?

For coding workloads, Leanstral 119B A6B on NVIDIA GH200 96GB receives a F grade with 71.1 tok/s and 21K context.

What context window can Leanstral 119B A6B use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Leanstral 119B A6B can safely use up to 32K tokens of context at NVFP4 quantization. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB 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-gh200-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: