whatmodel.sh / Qwen1.5 MoE A2.7B Chat

Qwen1.5 MoE A2.7B Chat

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

Qwen1.5 MoE A2.7B Chat is an open-weights language model from Alibaba, released March 2024. Its published size is 14.32B parameters (2.7B active per token) and a 33k-token context window. Licence: tongyi-qianwen.

Catalogue identity notes

Qwen/Qwen1.5-MoE-A2.7B-Chat @ec052fd (created 2024-03-14, licence tongyi-qianwen). Qwen's first MoE chat model (14.3B total, 2.7B activated per the 'A2.7B' name and the Qwen1.5-MoE blog). Single independent run: Open PT-LLM (142 catalogue models).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 14,315,784,192 parameters; active 2.7B from the maker's 'A2.7B' naming.

43.8±6.4#623 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Qwen1.5 MoE A2.7B Chat, out of 1132 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
777Code Tulu 2 34B Allen Institute for AI44±2local~72GB2023-11
778Snorkel-Mistral-PairRM-DPO Snorkel AI44±1local~6.1GB2024-01
779Qwen1.5 MoE A2.7B Chat Alibaba44±6local~10GB2024-03
780Qwen3 1.7B Alibaba44±1local~2.6GB2025-04
781Phi-4-mini 3.8B Microsoft44±1api $0.13/M +local~3.8GB2025-02
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

other tests1 not in a task · 82% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)62.6% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 97/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%at its level · 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 MoE A2.7B Chat · needs ~9.5 GB · from huggingface.co/1bit-MONSTER
    chat in the terminal
    llama cli -hf 1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf 1bit-MONSTER/Qwen1.5-MoE-A2.7B-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 MoE A2.7B Chat · needs ~9.5 GB · from huggingface.co/1bit-MONSTER

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/1bit-MONSTER/Qwen1.5-MoE-A2.7B-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 MoE A2.7B Chat · needs ~9.5 GB · from huggingface.co/1bit-MONSTER
    chat in the terminal
    ollama run hf.co/1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF: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 MoE A2.7B Chat · needs ~8.5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen1.5-MoE-A2.7B-Chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen1.5-MoE-A2.7B-Chat-4bit

Other ways to run it

  1. Run it as published · needs ~28.63 GB, NVIDIA only · from huggingface.co/Qwen (official)
    vllm serve Qwen/Qwen1.5-MoE-A2.7B-Chat

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Open Portuguese LLM Leaderboa… 82%

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
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%Apache-2.0
prior · pull toward the middle▇▇▇▇▇ 18%
weighted average= 43.8

$ 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