Qwen-14B-Chat

+ contribute

Qwen-14B-Chat is an open-weights language model from Alibaba, released September 2023. Its published size is 14.2B parameters. Licence: tongyi-qianwen.

Catalogue identity notes

Comparison-only. Arena entry 'qwen-14b-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'qwen-14b-chat' as 'Qwen-14B-Chat' (Alibaba, Qianwen LICENSE), linking https://huggingface.co/Qwen/Qwen-14B-Chat. Maker repo Qwen/Qwen-14B-Chat @cdaff79: licence tag none tagged. 14,167,290,880 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-09: month the maker's Hugging Face repo was created (createdAt 2023-09-24).

38.4±0.9#557 of 719 LLMsfrom 6 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Qwen-14B-Chat, out of 828 with a score, then more from Alibaba.

#	model	score	where	RAM	released
647	Llama-3-Instruct-8B-SimPO-v0.2 Princeton NLP	39±1	local	~6.6GB	2024-07
648	Llama 3.2 3B Instruct Meta	38±1	api $0.12/M +local	~3.4GB	2024-09
649	Qwen-14B-Chat Alibaba	38±1	local	~11GB	2023-09
650	Falcon-180B-Chat TII	38±2	local	~115GB	2023-09
651	CodeGemma 7B (v1.0) Google	38±1	local	~7.1GB	2024-03
	more from Alibaba
18	Qwen3.8 Max (2.4T-A95B) Alibaba	78±1	api $3.00/M +local	~380GB	2026-08
34	Qwen3.8 Max (0902) Alibaba	76±1	api $3.00/M		2026-09
37	Qwen3.8-Flash-Next Alibaba	75±1	local	~59GB	2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #378 of 458 * · 41% of its score · 1 test

Beats LFM2.5 8B-A1B, DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval	46.3% ✎	▁█▄▅▇█·▄▇▅▄▄ beats 18/42	easy · avg 78%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%	sharp · at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #355 of 393 · 34% of its score · 3 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-3-mini-4k-instruct (June 2024 update) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Qwen2.5 0.5B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
AlpacaEval 2 length-controlled	12.4% ✎	▁▂▂▃▆▆█▆▄▄▁▁ beats 30/122	medium · avg 39%	▇▇▇▇▇▇▇ 18%	typical
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	1081.0 ✎	▂▁▂▁▃▇█▆▇▄▂▂ beats 37/95	avg 1201	▇▇▇ 8.0%	blunt
LMArena (text)	1139.3 ✎	▁▁▁▃▃▃▃▆▆▇█▃ beats 32/379	avg 1268	▇▇▇ 7.9%	blunt

other tests2 not in a task · 24% of its score

test	result	vs the others in its run	difficulty	counts	why
EvoEval (overall)	32.1% ✎	▂▂▃▄▄█▁▄▅▃▁▃ beats 17/42	medium · avg 55%	▇▇▇▇▇▇▇▇ 21%	at its level
EQ-Bench v1 (60 questions, paper run)	43.8% ✎	▂··▄·▂▆▄▂█·▂ beats 8/14	medium · avg 57%	▇ 3.5%	at its level

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Qwen-14B-Chat · needs ~9.4 GB · from huggingface.co/mradermacher
chat in the terminal
llama cli -hf mradermacher/Qwen-14B-Chat-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/Qwen-14B-Chat-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Qwen-14B-Chat · needs ~9.4 GB · from huggingface.co/mradermacher
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/mradermacher/Qwen-14B-Chat-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Qwen-14B-Chat · needs ~9.4 GB · from huggingface.co/mradermacher
chat in the terminal
ollama run hf.co/mradermacher/Qwen-14B-Chat-GGUF:Q4_K_M

Other ways to run it

Run it as published · needs ~28.33 GB · from huggingface.co/Qwen (official)
pip install torch transformers==4.32.0 accelerate tiktoken einops scipy transformers_stream_generator==0.0.4 && python -c "from transformers import AutoModelForCausalLM, AutoTokenizer; t=AutoTokenizer.from_pretrained('Qwen/Qwen-14B-Chat', trust_remote_code=True); m=AutoModelForCausalLM.from_pretrained('Qwen/Qwen-14B-Chat', device_map='auto', trust_remote_code=True).eval(); print(m.chat(t, '你好', history=None)[0])"

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Top Leaderboard Ranking = Top… 62%, AlpacaEval 1.0 and 2.0 leader… 18%, Polyrating: A Cost-Effective… 8% and 2 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs	2	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%	CC BY 4.0
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)	1	▇▇▇▇▇ 18%	Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇▇ 8%	CC-BY-4.0
LMArena leaderboard dataset	1	▇▇ 8%	CC BY 4.0
EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs	1	▇ 3%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 38.4

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json