#1313th of 14 in Open models

qwen

First-generation Qwen open-weight LLMs, 1.8B to 72B, with inference and finetuning code

Live demo ↗ Documentation ↗ Repository on GitHub ↗

Stars: 21.9k
License: Apache-2.0
Last commit: Mar 2026
Language: Python

Missed the latest GitHub check; these facts may be older.

Overview

Repository for the original Qwen base and chat models at 1.8B, 7B, 14B and 72B, with Int4 and Int8 quantized chat variants on Hugging Face and ModelScope. It includes Transformers inference examples, LoRA and Q-LoRA finetuning, vLLM and FastChat deployment, and a web demo. The repo is no longer actively maintained; development moved to QwenLM/Qwen2.

Who it is for: Engineers needing legacy Qwen-1 weights or reference finetuning code

Strengths

Four sizes (1.8B, 7B, 14B, 72B) with base, chat, Int4 and Int8 checkpoints
Context up to 32K on 1.8B, 7B and 72B; Q-LoRA finetune of 1.8B needs 5.8GB
Includes finetuning scripts: full-parameter, LoRA and Q-LoRA
Chat models support tool use, agent and code interpreter modes

Weaknesses

No longer actively maintained; README points to QwenLM/Qwen2
Requires trust_remote_code=True to load models
Qwen-14B context is 8K; Qwen-72B Int4 generation needs 48.9GB GPU memory
No tagged releases; README says RLHF chat models not released yet

What it needs

GPU optional
Docker
Needs PyTorch, Transformers, flash-attention (optional), vLLM (optional), FastChat (optional)
Models: Qwen-1.8B, Qwen-7B, Qwen-14B, Qwen-72B, Qwen-Chat

Also in Open models

See all 14

Also in Open models
Rank	Project	Score
1	llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU37.9k starsMIT	84 out of 100
2	layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions Live demo ↗ (opens in a new tab)32.9k starsApache-2.0	79 out of 100
3	timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research34.5k starsApache-2.0	72 out of 100
#4	unlimited-ocrOCR model that parses long documents and multi-page PDFs in one pass Live demo ↗ (opens in a new tab)27.3k starsMIT	62 out of 100
#5	insightfaceFace detection, recognition and alignment toolbox with ArcFace and RetinaFace models Live demo ↗ (opens in a new tab)29.9k starsno license	57 out of 100

How to choose

Read the license: open weights are not always open for commercial use.
Check the hardware the model needs at the precision you plan to run.
See whether the repo ships inference code or only weights.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

Apache-2.0 Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

Where to run it

Vast.ai ↗ (opens in a new tab)Rent a GPU by the hour from a marketplace of hosts.

Referral links: if you sign up through one, we get a commission. They never change a rank.

#13 of 14 in Open models on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/qwenlm/qwen.svg)](https://archestack.com/best-of-ai/projects/qwen/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/qwen/" title="qwen on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with qwen filled in.