whatmodel.sh / GLM-4 9B Chat 1M

GLM-4 9B Chat 1M

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

GLM-4 9B Chat 1M is an open-weights language model from Zhipu AI (THUDM), released June 2024. Its published size is 9.48B parameters and a 1M-token context window. Licence: other (glm-4).

Catalogue identity notes

Maker repo zai-org/glm-4-9b-chat-1m @f8579ac (requested as THUDM/glm-4-9b-chat-1m, which the HF API redirects to zai-org/glm-4-9b-chat-1m): licence tag other (glm-4). 9,483,857,952 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-06: month the maker's Hugging Face repo was created (createdAt 2024-06-04).

53.4±4.7#292 of 719 LLMsfrom 3 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of GLM-4 9B Chat 1M, out of 828 with a score, then more from Zhipu AI (THUDM).

#modelscorewhereRAMreleased
347DeepSeek-V2.5 DeepSeek54±1local~151GB2024-09
348DeepSeek-V2 Chat (0628) DeepSeek54±1local~66GB2024-07
349GLM-4 9B Chat 1M Zhipu AI (THUDM)53±5local~8.1GB2024-06
350Mistral Small 3 24B (2501) Mistral53±1local~16GB2025-01
351Qwen2-VL 72B Instruct Alibaba53±1local~34GB2024-09
more from Zhipu AI (THUDM)
485CogVLM2 Llama3 Chinese Chat 19B Zhipu AI (THUDM)47±7comparison only2024-05
569CogVLM2 Llama3 Chat 19B Zhipu AI (THUDM)43±3local~43GB2024-05
706ChatGLM3 6B 128K Zhipu AI (THUDM)34±4local~5.8GB2024-01

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 90% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)74.1% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 212/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%at its level · noisy
RULER 64k86.7% ✎▁▁·▁·▂▃▄█▂·▁ beats 19/22easy · avg 83%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 36%typical
RULER 128k83.1% ✎▄··▂▄▂▆██▄▄▂ beats 19/21easy · avg 68%▇▇▇▇▇▇ 15%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 GLM-4 9B Chat 1M · needs ~6.3 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/glm-4-9b-chat-1m-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/glm-4-9b-chat-1m-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 GLM-4 9B Chat 1M · needs ~6.3 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/glm-4-9b-chat-1m-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 GLM-4 9B Chat 1M · needs ~6.3 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/glm-4-9b-chat-1m-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~18.97 GB · from huggingface.co/zai-org
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='zai-org/glm-4-9b-chat-1m', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/zai-org ↗

$ how the score was worked out · NVIDIA RULER repository READM… 50%, Open Portuguese LLM Leaderboa… 40%

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
NVIDIA RULER repository README results table2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇▇▇▇ 40%Apache-2.0
prior · pull toward the middle▇▇▇ 10%
weighted average= 53.4

$ 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