whatmodel.sh / Qwen1.5 1.8B Chat

Qwen1.5 1.8B Chat

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

Qwen1.5 1.8B Chat is an open-weights language model from Alibaba, released January 2024. Its published size is 1.84B parameters and a 33k-token context window. Licence: tongyi-qianwen-research.

Catalogue identity notes

Qwen/Qwen1.5-1.8B-Chat @e482ee3 (created 2024-01-30, licence tongyi-qianwen-research). Qwen1.5 1.8B chat model, sibling of the catalogued Qwen1.5 4B/7B/14B/32B/72B/110B chat entries. Independent rows: LiveBench 2024-07-26, Open PT-LLM, EuroEval, AlpacaEval 2.0.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 1,836,828,672 parameters (Qwen/Qwen1.5-1.8B-Chat @e482ee3).

23.8±2.4#680 of 719 LLMsfrom 4 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Qwen1.5 1.8B Chat, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
784Falcon3 1B Instruct TII24±4local~2.4GB2024-12
785StableLM-Base-Alpha 3B v2 Stability AI24±1local~13GB2023-08
786Qwen1.5 1.8B Chat Alibaba24±2local~2.7GB2024-01
787Pythia 6.9B EleutherAI23±1local~6.1GB2023-02
788OpenAssistant SFT-4 Pythia 12B LAION (OpenAssistant)22±1local~9.5GB2023-04
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▁▃▁▃▅▄▅█▆▆▇▃ #388 of 393 * · 30% of its score · 1 test

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

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled2.6% ✎▃▂▂▃▆▆█▆▄▄▁▁ beats 1/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇ 30%too hard for it
other tests3 not in a task · 67% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-266.0% ✎▃▁▁▂▂▃▂█▆▃▅▃ beats 1/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%too hard for it
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy57.2% ✎▁▁▁▁▁▁▁▃▄█▄▃ beats 28/146easy · avg 83%▇▇ 5.9%at its level · noisy
Open PT-LLM Leaderboard average (9 Portuguese tasks)43.2% ✎▃▁▁▁▁▁▃▁▂█▅▁ beats 53/276medium · avg 73%▇▇ 5.8%noisy

$ where to run it

llama.cpp · recommended

  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 1.8B Chat · needs ~1.22 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen1.5-1.8B-Chat-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf Qwen/Qwen1.5-1.8B-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 1.8B Chat · needs ~1.22 GB · from huggingface.co/Qwen (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Qwen1.5 1.8B Chat · needs ~1.1 GB · from ollama.com
    chat in the terminal
    ollama run qwen:1.8b

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 1.8B Chat · needs ~1.5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen1.5-1.8B-Chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen1.5-1.8B-Chat-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · LiveBench model judgments (HF… 56%, AlpacaEval 1.0 and 2.0 leader… 30%, EuroEval leaderboards (result… 6% and 1 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%Apache-2.0 (stated in the LiveBench datasheet)
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇ 30%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard1▇▇ 6%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 23.8

$ 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