Can DeepSeek V2.5 236B run on RTX 3090 Ti 24GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

DeepSeek V2.5 236B needs ~205.9 GB but RTX 3090 Ti 24GB only has 24.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: HighStack: StandardBottleneck: Memory capacity

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) — 205.9 GB, exceeds 24.0 GB available

205.9 GB required24.0 GB available

858% VRAM needed

181.9 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.0 tok/s

TTFT

96367 ms

Safe context

Memory

205.9 GB / 24.0 GB

Offload

90%

Memory breakdown

Weights144.0 GB

KV Cache58.6 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsDeepSeek V2.5 236B on RTX 3090 Ti 24GB
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: 2.0 tok/s decode · 96.4s TTFT (warm) · 5 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 205.9 GB, but this setup only exposes 24.0 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	2.0 tok/s	52564 ms	4K
Coding	F	Too heavy	2.0 tok/s	96367 ms	4K
Agentic Coding	F	Too heavy	2.0 tok/s	140170 ms	4K
Reasoning	F	Too heavy	2.0 tok/s	113888 ms	4K
RAG	F	Too heavy	2.0 tok/s	175213 ms	4K

Quantization options

How DeepSeek V2.5 236B (236B params) fits at each quantization level on RTX 3090 Ti 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	92.0 GB	Low	F0
Q3_K_S	3	115.6 GB	Low	F0
NVFP4	4	132.2 GB	Medium	F0
Q4_K_M	4	144.0 GB	Medium	F0
Q5_K_M	5	169.9 GB	High	F0
Q6_K	6	193.5 GB	High	F0
Q8_0	8	252.5 GB	Very High	F0
F16	16	483.8 GB	Maximum	F0

Opciones de mejora

Hardware que ejecuta bien DeepSeek V2.5 236B

AMD Instinct MI350X 288GBOpción económica

288 GB VRAM (+264)8000 GB/s (+6992)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.109.3 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$8,000 MSRP

B100 192GBMejor relación calidad-precio

192 GB VRAM (+168)8000 GB/s (+6992)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.84 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Sube la velocidad estimada de decodificación alrededor de un 4100%.

~$35,000 MSRP

NVIDIA GB200 192GBMejora NVIDIA

192 GB VRAM (+168)8000 GB/s (+6992)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.84 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Sube la velocidad estimada de decodificación alrededor de un 4100%.

~$60,000 MSRP

Frequently asked questions

Can RTX 3090 Ti 24GB run DeepSeek V2.5 236B?

No, DeepSeek V2.5 236B requires more memory than RTX 3090 Ti 24GB provides.

How much VRAM does DeepSeek V2.5 236B need?

DeepSeek V2.5 236B (236B parameters) requires approximately 205.9 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek V2.5 236B?

The recommended quantization for DeepSeek V2.5 236B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek V2.5 236B run at on RTX 3090 Ti 24GB?

On RTX 3090 Ti 24GB, DeepSeek V2.5 236B achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 96367ms using Q4_K_M quantization.

Can RTX 3090 Ti 24GB run DeepSeek V2.5 236B for coding?

For coding workloads, DeepSeek V2.5 236B on RTX 3090 Ti 24GB receives a F grade with 2.0 tok/s and 4K context.

What context window can DeepSeek V2.5 236B use on RTX 3090 Ti 24GB?

On RTX 3090 Ti 24GB, DeepSeek V2.5 236B can safely use up to 4K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if DeepSeek V2.5 236B feels slow on RTX 3090 Ti 24GB?

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.

See all results for RTX 3090 Ti 24GB See all hardware for DeepSeek V2.5 236B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-v2.5-236b-on-rtx-3090-ti-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: