Check my GPU

LLMs ·

Qwen3 14B

Parameters
15B
Architecture
Dense
Max context
32K tokens
License
apache-2.0
Released
2025-04

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run qwen3:14b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/Qwen/Qwen3-14B-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen3-14B-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3-14B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen3 (opens in a new tab)

git clone https://github.com/QwenLM/Qwen3

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 5.9 GB 7.9 GB 11.9 GB GGUF files (opens in a new tab)
Q3_K_M Low 7.3 GB 9.2 GB 13.2 GB GGUF files (opens in a new tab)
Q4_K_M Good 9.0 GB 11.0 GB 15.0 GB GGUF (opens in a new tab)
Q5_K_M High 10.5 GB 12.5 GB 16.5 GB GGUF (opens in a new tab)
Q6_K High 12.1 GB 14.1 GB 18.1 GB GGUF (opens in a new tab)
Q8_0 Very high 15.7 GB 17.6 GB 21.7 GB GGUF (opens in a new tab)
F16 Full 29.6 GB 31.5 GB 35.6 GB Original weights (opens in a new tab)

Best hardware for Qwen3 14B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q3_K_M.

Grade · points Hardware Quant Memory Speed Fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 18.8 GB / 24.0 GB 42.6 tok/s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 18.8 GB / 24.0 GB 39.5 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15 AMD Radeon RX 7900 XTX Q6_K 15.3 GB / 24.0 GB 47.6 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M 13.3 GB / 16.0 GB 46.0 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q5_K_M 13.3 GB / 16.0 GB 50.4 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q5_K_M 13.3 GB / 16.0 GB 61.4 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q5_K_M 13.3 GB / 16.0 GB 65.8 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15 NVIDIA GeForce RTX 5090 Q8_0 19.2 GB / 32.0 GB 75.7 tok/s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q5_K_M 13.3 GB / 16.0 GB 37.8 tok/s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB Q4_K_M 11.8 GB / 16.0 GB 37.2 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.