whatmodel.sh / Qwen1.5 4B Chat

Qwen1.5 4B Chat

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Qwen1.5 4B Chat is an open-weights language model from Alibaba, released February 2024. Its published size is 3.95B parameters and a 32k-token context window. Licence: tongyi-qianwen-research.

Catalogue identity notes

Arena entry 'qwen1.5-4b-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'qwen1.5-4b-chat' as 'Qwen1.5-4B-Chat' (Alibaba, Qianwen LICENSE), linking https://qwenlm.github.io/blog/qwen1.5/. Maker repo Qwen/Qwen1.5-4B-Chat @a7a4d49: licence tag other (tongyi-qianwen-research). 3,950,369,280 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-02: Qwen blog qwenlm.github.io/blog/qwen1.5/ (datePublished 2024-02-04).

31.9±1.6#627 of 719 LLMsfrom 5 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Qwen1.5 4B Chat, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
722Gemma 7B IT Google32±1local~7.1GB2024-02
723Mistral 7B Instruct v0.1 Mistral32±1local~6.1GB2023-09
724Qwen1.5 4B Chat Alibaba32±2local~4.1GB2024-02
725Ghost 7B Alpha Ghost X32±2local~6.1GB2024-04
726CodeGemma 2B (v1.0) Google32±1local~3.2GB2024-03
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▃▃▅▄▅█▆▆▇▃ #380 of 393 * · 46% of its score · 2 tests

Beats Phi-2 (2.7B) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1026.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 17/95avg 1201▇▇▇▇▇▇▇▇▇ 23%blunt
LMArena (text)1091.1 ✎▁▁▃▂▃▃▃▆▆▇█▃ beats 14/379avg 1268▇▇▇▇▇▇▇▇▇ 23%blunt
other tests3 not in a task · 53% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2611.3% ✎▁▁▁▃▂▃▂█▆▃▅▃ beats 5/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%typical
Open PT-LLM Leaderboard average (9 Portuguese tasks)61.3% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 93/276medium · avg 73%▇▇ 3.9%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy72.8% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 44/146easy · avg 83%▇ 3.5%at its level · noisy

$ where to run it

llama.cpp · recommended

version

  1. 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 ↗

  2. Run Qwen1.5 4B Chat · needs ~2.5 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen1.5-4B-Chat-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf Qwen/Qwen1.5-4B-Chat-GGUF:q4_k_m

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Qwen1.5 4B Chat · needs ~2.5 GB · from huggingface.co/Qwen (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/Qwen/Qwen1.5-4B-Chat-GGUF@q4_k_m -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Qwen1.5 4B Chat · needs ~2.87 GB · from ollama.com
    chat in the terminal
    ollama run qwen:4b-chat-v1.5-q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Qwen1.5 4B Chat · needs ~2.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen1.5-4B-Chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen1.5-4B-Chat-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · LiveBench model judgments (HF… 45%, Polyrating: A Cost-Effective… 23%, LMArena leaderboard dataset 23% 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

sourceresultsshare of the scorelicence
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%Apache-2.0 (stated in the LiveBench datasheet)
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇ 23%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇ 23%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 4%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard1▇ 4%MIT
prior · pull toward the middle▇ 1%
weighted average= 31.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit 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 · sources and licences · json