VOOZH about

URL: https://willitrunai.com/can-run/leanstral-119b-a6b-on-rtx-4070-ti-super-16gb

⇱ Leanstral 119B A6B on RTX 4070 Ti Super 16GB? No — Alternat…

Can Leanstral 119B A6B run on RTX 4070 Ti Super 16GB?

NO — Won't Fit

F0Won't run
○Estimated from fit model

Leanstral 119B A6B needs ~85.4 GB but RTX 4070 Ti Super 16GB only has 16.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: MediumStack: OptimizedBottleneck: Memory capacity
Share:

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) — 85.4 GB, exceeds 16.0 GB available
85.4 GB required16.0 GB available
534% VRAM needed

69.4 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.5 tok/s

TTFT

78812 ms

Safe context

4K

Memory

85.4 GB / 16.0 GB

Offload

80%

Memory breakdown

Weights72.6 GB
KV Cache8.8 GB
Runtime2.4 GB
Headroom1.6 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsLeanstral 119B A6B on RTX 4070 Ti Super 16GB
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: 2.5 tok/s decode · 78.8s TTFT (warm) · 6 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 85.4 GB, but this setup only exposes 16.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy2.5 tok/s42989 ms4K
CodingFToo heavy2.5 tok/s78812 ms4K
Agentic CodingFToo heavy2.5 tok/s114636 ms4K
ReasoningFToo heavy2.5 tok/s93142 ms4K
RAGFToo heavy2.5 tok/s143295 ms4K

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on RTX 4070 Ti Super 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
46.4 GB
LowF0
Q3_K_S
3
58.3 GB
LowF0
NVFP4
4
66.6 GB
MediumF0
Q4_K_M
4
72.6 GB
MediumF0
Q5_K_M
5
85.7 GB
HighF0
Q6_K
6
97.6 GB
HighF0
Q8_0
8
127.3 GB
Very HighF0
F16
16
244.0 GB
MaximumF0

Upgrade options

Hardware that runs Leanstral 119B A6B well

👁 NVIDIA
NVIDIA H200 141GBBudget pick
141 GB VRAM (+125)4800 GB/s (+4128)
S
Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s decode

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

👁 NVIDIA
NVIDIA H200 PCIe 141GBBest value
141 GB VRAM (+125)4800 GB/s (+4128)
S
Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s decode

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

👁 NVIDIA
NVIDIA DGX Spark 128GBNVIDIA upgrade
128 GB Unified (+112)
A
Makes the model fit on the accelerator instead of staying completely out of reach.5 tok/s decode

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Frequently asked questions

See all results for RTX 4070 Ti Super 16GBSee all hardware for Leanstral 119B A6B