Alibaba/Dense

Qwen3 14B

Qwen3 14B — dual-mode reasoning, very strong benchmarks for its size.

chatreasoningThinkingTool Use

14.8B

Parameters

32K

Context length

20

Benchmarks

10

Quantizations

600K

HF downloads

Architecture

Dense

Released

2025-04-28

Layers

40

KV Heads

8

Head Dim

128

Family

qwen

Quantization Options

Quant	Bits	VRAM	Quality
Q3_K_M	4	7.9 GB	low
Q3_K_L	4.3	8.4 GB	moderate
IQ4_XS	4.46	8.7 GB	moderate
Q4_K_S	4.67	9.1 GB	moderate
Q4_K_M	4.89	9.5 GB	good
Q5_K_S	5.57	10.8 GB	good
Q5_K_M	5.7	11.0 GB	good
Q6_K	6.56	12.6 GB	excellent
Q8_0	8.5	16.2 GB	lossless
FP16	16	30.1 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN3 14B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (20)

MATH91.0

HumanEval88.0

MATH-50087.1

IFEval82.0

BBH65.5

MMLU-PRO62.0

AIME58.0

AA Math58.0

GPQA52.0

GPQA Diamond47.0

BigCodeBench39.8

MUSR38.7

τ²-Bench32.2

LiveCodeBench28.0

SciCode26.5

IFBench23.9

AA Intelligence12.8

AA Coding12.4

Terminal-Bench5.3

HLE4.2

Run this model

▸Easiest way to get started·Beginners

curl -fsSL https://ollama.com/install.sh | sh

$ollama run qwen3:14b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 3080 10GB

10 GB VRAM • 760 GB/s

NVIDIA

$429

Amazon Newegg eBay PCPartPicker

10 GB VRAM • 456 GB/s

INTEL

$219

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 3080

10 GB VRAM • 760 GB/s

NVIDIA

$699

Amazon Newegg eBay PCPartPicker

AMD Radeon RX 6700

10 GB VRAM • 320 GB/s

AMD

$299

Amazon Newegg eBay PCPartPicker

AMD Radeon RX 6700M

10 GB VRAM • 320 GB/s

AMD

Amazon Newegg eBay PCPartPicker

AMD Radeon RX 6750 GRE 10 GB

10 GB VRAM • 320 GB/s

AMD

$229

Amazon Newegg eBay PCPartPicker

NVIDIA P102-101

10 GB VRAM • 320 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

AMD Xbox Series X GPU

10 GB VRAM • 560 GB/s

AMD

Amazon Newegg eBay PCPartPicker

NVIDIA CMP 170HX 10 GB

10 GB VRAM • 1560 GB/s

NVIDIA

NVIDIA CMP 50HX

10 GB VRAM • 560 GB/s

NVIDIA

NVIDIA CMP 90HX

10 GB VRAM • 760 GB/s

NVIDIA

AMD Xbox Series X 6nm GPU

10 GB VRAM • 560 GB/s

AMD

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 2080 Ti

11 GB VRAM • 616 GB/s

NVIDIA

$350

Amazon Newegg eBay PCPartPicker

NVIDIA GTX 1080 Ti

11 GB VRAM • 484 GB/s

NVIDIA

$200

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce GTX 1080 Ti

11 GB VRAM • 484 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 2080 Ti

11 GB VRAM • 616 GB/s

NVIDIA

$225

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 5070

12 GB VRAM • 672 GB/s

NVIDIA

$549

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 4070 Ti

12 GB VRAM • 504 GB/s

NVIDIA

$799

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 4070 SUPER

12 GB VRAM • 504 GB/s

NVIDIA

$599

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 4070

12 GB VRAM • 504 GB/s

NVIDIA

$549

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 3080 Ti

12 GB VRAM • 912 GB/s

NVIDIA

$550

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 3080 12GB

12 GB VRAM • 912 GB/s

NVIDIA

$599

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 3060 12GB

12 GB VRAM • 360 GB/s

NVIDIA

$329

Amazon Newegg eBay PCPartPicker

12 GB VRAM • 432 GB/s

AMD

$449

Amazon Newegg eBay PCPartPicker

12 GB VRAM • 384 GB/s

AMD

$344

Amazon Newegg eBay PCPartPicker

12 GB VRAM • 432 GB/s

AMD

$299

Amazon Newegg eBay PCPartPicker

12 GB VRAM • 456 GB/s

INTEL

$249

Amazon Newegg eBay PCPartPicker

NVIDIA Tesla K40c

12 GB VRAM • 288 GB/s

NVIDIA

NVIDIA Tesla K40d

12 GB VRAM • 288 GB/s

NVIDIA

NVIDIA Tesla K40m

12 GB VRAM • 288 GB/s

NVIDIA

Find the best GPU for Qwen3 14B

Build Hardware for Qwen3 14B

Model Card

View on HuggingFace

Qwen3 14B — dual-mode reasoning, very strong benchmarks for its size.

▸ SPEC SHEET

Qwen3 14B — 14.8B Dense.

▸ SPECIFICATIONS

PARAMETERS: 14.8B
ARCHITECTURE: Dense Transformer
CONTEXT LENGTH: 32K tokens
CAPABILITIES: chat, reasoning
RELEASE DATE: 2025-04-28
PROVIDER: Alibaba
FAMILY: qwen

▸ VRAM REQUIREMENTS

QUANT	BPW	VRAM	QUALITY
Q3_K_M	4	7.9 GB	88%
Q3_K_L	4.3	8.4 GB	90%
IQ4_XS	4.46	8.7 GB	92%
Q4_K_S	4.67	9.1 GB	93%
Q4_K_M	4.89	9.5 GB	94%
Q5_K_S	5.57	10.8 GB	96%
Q5_K_M	5.7	11.0 GB	96%
Q6_K	6.56	12.6 GB	97%
Q8_0	8.5	16.2 GB	100%
FP16	16	30.1 GB	100%

§ 01BENCHMARK SCORES

HumanEval88.0

MMLU-PRO62.0

MATH91.0

IFEval82.0

BBH65.5

GPQA52.0

MUSR38.7

BigCodeBench39.8

GPQA Diamond47.0

LiveCodeBench28.0

AIME58.0

MATH-50087.1

HLE4.2

AA Intelligence12.8

AA Coding12.4

AA Math58.0

aa_ifbench23.9

aa_terminal_bench5.3

aa_tau232.2

aa_scicode26.5

§ 02RUN COMMAND

Run Qwen3 14B locally with Ollama — needs 9.5 GB VRAM at Q4_K_M:

$ollama run qwen3:14b

§ 03COMPATIBLE GPUs

30 @ Q4_K_M

NVIDIA RTX 3080 10GB

10 GB · 760 GB/s

10 GB · 456 GB/s

NVIDIA GeForce RTX 3080

10 GB · 760 GB/s

AMD Radeon RX 6700

10 GB · 320 GB/s

AMD Radeon RX 6700M

10 GB · 320 GB/s

AMD Radeon RX 6750 GRE 10 GB

10 GB · 320 GB/s

NVIDIA P102-101

10 GB · 320 GB/s

AMD Xbox Series X GPU

10 GB · 560 GB/s

NVIDIA CMP 170HX 10 GB

10 GB · 1560 GB/s

NVIDIA CMP 50HX

10 GB · 560 GB/s

NVIDIA CMP 90HX

10 GB · 760 GB/s

AMD Xbox Series X 6nm GPU

10 GB · 560 GB/s

NVIDIA RTX 2080 Ti

11 GB · 616 GB/s

NVIDIA GTX 1080 Ti

11 GB · 484 GB/s

NVIDIA GeForce GTX 1080 Ti

11 GB · 484 GB/s