whatmodel.sh / FuseChat-Qwen-2.5-7B-Instruct

FuseChat-Qwen-2.5-7B-Instruct

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

FuseChat-Qwen-2.5-7B-Instruct is an open-weights language model from FuseAI, released November 2024. Its published size is 7.62B parameters.

Catalogue identity notes

Maker repo FuseAI/FuseChat-Qwen-2.5-7B-Instruct @04deffb: no licence tag on the card. 7,615,616,512 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-11: month the maker's Hugging Face repo was created (createdAt 2024-11-12).

59.3±1.6#231 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 FuseChat-Qwen-2.5-7B-Instruct, out of 1132 with a score, then more from FuseAI.

#modelscorewhereRAMreleased
301DeepSeek V3 (Dec '24) DeepSeek59±1api $0.46/M +local~337GB2024-12
302Step 3 StepFun59±3local~346GB2025-07
303FuseChat-Qwen-2.5-7B-Instruct FuseAI59±2local~6.4GB2024-11
304Gemma 2 9B IT SimPO Princeton NLP59±1local~7.6GB2024-07
305Hunyuan-TurboS (20250226) Tencent59±3comparison only2025-02
more from FuseAI
250FuseChat-Gemma-2-9B-Instruct FuseAI62±2local~7.6GB2024-11
288FuseChat-Llama-3.1-8B-Instruct FuseAI60±2local~6.6GB2024-11
398FuseChat-Llama-3.2-3B-Instruct FuseAI56±2local~3.4GB2024-12

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #159 of 466 * · 99% of its score · 1 test

Beats MiniMax-M2, MiniCPM5 2B, Granite 4.2 30B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled63.6% ✎▁▂▂▃▆▆█▆▄▄▃▁ beats 117/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%at its level

$ 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 FuseChat-Qwen-2.5-7B-Instruct · needs ~4.7 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/FuseChat-Qwen-2.5-7B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/FuseChat-Qwen-2.5-7B-Instruct-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 FuseChat-Qwen-2.5-7B-Instruct · needs ~4.7 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/FuseChat-Qwen-2.5-7B-Instruct-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 FuseChat-Qwen-2.5-7B-Instruct · needs ~4.7 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/FuseChat-Qwen-2.5-7B-Instruct-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~15.23 GB · from huggingface.co/FuseAI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='FuseAI/FuseChat-Qwen-2.5-7B-Instruct', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/FuseAI ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 99%

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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 59.3

$ 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