Can Leanstral 119B A6B run on NVIDIA B200 180GB?

YES — Runs Great

S90Excellent

○Estimated from fit model

Leanstral 119B A6B needs ~101.8 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~205 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) — 101.8 GB, 204.7 tok/s, Runs well

101.8 GB required180.0 GB available

57% VRAM used

Fit status

Runs well

Decode

204.7 tok/s

TTFT

946 ms

Safe context

158K

Memory

101.8 GB / 180.0 GB

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsLeanstral 119B A6B on NVIDIA B200 180GB
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: 204.7 tok/s decode · 946ms TTFT (warm) · 512 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	Runs well	204.7 tok/s	516 ms	158K
Coding	S	Runs well	204.7 tok/s	946 ms	158K
Agentic Coding	S	Runs well	204.7 tok/s	1376 ms	158K
Reasoning	S	Runs well	204.7 tok/s	1118 ms	158K
RAG	S	Runs well	204.7 tok/s	1720 ms	158K

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A77
Q3_K_S	3	58.3 GB	Low	A79
NVFP4	4

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 NVIDIA B200 180GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	77.9 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S

Frequently asked questions

See all results for NVIDIA B200 180GB See all hardware for Leanstral 119B A6B

URL: https://willitrunai.com/can-run/leanstral-119b-a6b-on-b200-180gb

⇱