Can Qwen3 14B run locally?

Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen3-14B. Ollama, LM Studio, llama.cpp, MLX-LM and KTransformers all support it.

What does it cost and what is the context window?

Via API it is $0.12 per million input tokens and $0.24 per million output tokens. The native context is 32,768 tokens, extendable to 131,072 with YaRN-based scaling.

How is Qwen3 14B different from Qwen2.5?

Qwen3 14B adds the explicit thinking/non-thinking mode switch, which Qwen2.5 instruct models lack, and the maker states it surpasses previous Qwen2.5 instruct models on math, code and commonsense reasoning.

Qwen3 14B

4339°

#llm #qwen #reasoning #coding #agents #multilingual

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Qwen | 40,960 token context | $0.12/M input, $0.24/M output. Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Qwen3 14B is a 14.8-billion-parameter open-weights model from Qwen that runs in two explicit modes: a thinking mode for math, code and multi-step reasoning, and a non-thinking mode for ordinary conversation. At $0.12 per million input tokens via API, and fully runnable on local hardware through Ollama, LM Studio or llama.cpp, it sits in a practical middle ground between small fast models and large expensive ones. It suits developers and researchers who want a single model that can switch gears without swapping checkpoints.

Known for

Switchable thinking and non-thinking modes within one model
Strong agent tool-use in both thinking and non-thinking modes
100+ language support with solid multilingual instruction-following
Open weights, runs locally via Ollama, LM Studio, llama.cpp and others
Native 32K context, extendable to 131K with YaRN scaling

Watch out for

Context beyond 32K uses YaRN extrapolation; quality at the far end is not guaranteed.
At 14.8B parameters, local use needs roughly 12–16 GB of VRAM for comfortable inference.
The maker has not published full licence terms on this page; check the Hugging Face repo before commercial use.

Best for

Prompts to try

Debug a tricky async bug

I have a Python async function that intermittently raises RuntimeError: Event loop is closed when called from a FastAPI background task. Walk through the likely causes step by step, then give me a corrected version of the pattern that avoids the issue. Use thinking mode if you can.

Plan a multi-step agent

You have access to a web search tool, a Python executor and a file-write tool. A user wants a weekly digest of AI research papers emailed every Monday. Design the full agent loop: what each step calls, what it checks, how it handles failures, and what the final output looks like.

Translate and localize copy

Translate the following English product description into Brazilian Portuguese, Mexican Spanish and Simplified Chinese. After each translation, add one short note on any cultural or idiomatic adjustment you made and why: 'Our app helps small teams ship faster by cutting meeting time in half and keeping everyone aligned without the noise.'

Compare with

Qwen3.8 Max (0902)
API-only model
1,000,000 token context · $2.00/M input, $6.00/M output
Qwen3.7 Plus
API-only model
1,000,000 token context · $0.32/M input, $1.28/M output
Qwen3.6 Plus
API-only model
1,000,000 token context · $0.33/M input, $1.95/M output
Qwen3.6 Max Preview
API-only model
262,144 token context · $1.03/M input, $6.16/M output

More text models from qwen

Questions people ask

Can Qwen3 14B run locally?: Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen3-14B. Ollama, LM Studio, llama.cpp, MLX-LM and KTransformers all support it.
What does it cost and what is the context window?: Via API it is $0.12 per million input tokens and $0.24 per million output tokens. The native context is 32,768 tokens, extendable to 131,072 with YaRN-based scaling.
How is Qwen3 14B different from Qwen2.5?: Qwen3 14B adds the explicit thinking/non-thinking mode switch, which Qwen2.5 instruct models lack, and the maker states it surpasses previous Qwen2.5 instruct models on math, code and commonsense reasoning.

Captain's verdict
A genuinely dual-mode open model at a price that makes it hard to ignore for anyone doing reasoning work on a budget.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Nemotron 3.5 Content Safety

TEXT / LLM

AI Models for Image, Video & Text Generation

Qwen3 14B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm qwen reasoning coding agents multilingual local

Browse by Model Family