CanItRun Logocanitrun.

Qwen3 14B

Qwen3 14B needs roughly 10.8 GB VRAM at Q4_K_M quantization (34.7 GB at FP16). 99 GPUs we track can run it fully in VRAM at 8k context.

99 GPUs run this natively · 5 with CPU offload

Alibaba14.8B params128k contextApache 2.0Commercial use ok

Qwen3 14B is a 14.8B parameter dense large language model developed by Alibaba. Released in April 2025, it is a text-only model with a 128K context window, released under the Apache 2.0 license, allowing commercial use. Supports thinking and non-thinking modes.

To run Qwen3 14B locally, you need approximately 10.8 GB of VRAM at Q4_K_M quantization with 8k context. 99 of the GPUs we track can run it fully in VRAM, with a further 5 able to offload to system RAM. At Q4_K_M it needs just 10.8 GB, making it accessible even on mid-range 16 GB cards like RTX 4080 and RTX 4070 Ti Super. At Q8_K_M (18.1 GB), you get near-FP16 quality while still fitting on 24, 48 and 80 GB GPUs. FP16 requires 34.7 GB, limiting it to 48 and 80 GB GPUs.

With an MMLU-Pro score of 61.03, it delivers strong general reasoning for local deployment. The license allows commercial use.

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP3259.2 GB1.34 GB67.8 GB
BF1629.6 GB1.34 GB34.7 GB
FP1629.6 GB1.34 GB34.7 GB
Q8_014.8 GB1.34 GB18.1 GB
Q6_K12.1 GB1.34 GB15.1 GB
Q5_K_Mrec9.5 GB1.34 GB12.2 GB
Q4_K_M8.3 GB1.34 GB10.8 GB
Q3_K_M6.4 GB1.34 GB8.6 GB
Q2_K4.9 GB1.34 GB7.0 GB
NVFP4cuda7.4 GB1.34 GB9.8 GB

KV cache shown at 8k context (FP16). NVFP4 requires a CUDA GPU. Enable TurboQuant in the calculator to see reduced KV cache estimates.

Benchmarks

MMLU-Pro
61.03

GPUs that run Qwen3 14B natively (99)

Plus 5 GPUs that run it with CPU offload (slower)

Notes

Supports thinking and non-thinking modes.

Hugging Face ↗Ollama ↗Released 2025-04-29

Frequently asked questions

What are the VRAM requirements for Qwen3 14B?
Qwen3 14B requires approximately 10.8 GB of VRAM at Q4_K_M quantization, 18.1 GB at Q8, and 34.7 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Qwen3 14B have?
Qwen3 14B has 14.8 billion parameters.
How capable is Qwen3 14B?
With an MMLU-Pro score of 61.03, Qwen3 14B delivers solid general-purpose performance suitable for most everyday tasks and professional use.
Can Qwen3 14B run on a 16 GB GPU?
Yes. Qwen3 14B needs 10.8 GB at Q4_K_M, which fits in a 16 GB GPU like the RTX 4080 or RTX 4070 Ti Super.
What is the smallest quantization for Qwen3 14B that fits in 24 GB of VRAM?
At NVFP4, Qwen3 14B needs 9.8 GB — the highest-quality quantization that fits in 24 GB of VRAM.
What GPU do I need to run Qwen3 14B locally?
A 16 GB GPU is enough. At Q4_K_M, Qwen3 14B needs 10.8 GB VRAM. Good options: RTX 4080 (16 GB), RTX 4070 Ti Super (16 GB).