whatmodel.sh / InternLM2 Chat 20B

InternLM2 Chat 20B

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

InternLM2 Chat 20B is an open-weights language model from Shanghai AI Laboratory (InternLM), released January 2024. Its published size is 19.86B parameters. Licence: other.

Catalogue identity notes

Maker repo internlm/internlm2-chat-20b @d606d41: licence tag other. 19,861,149,696 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-10).

40.9±1.4#517 of 719 LLMsfrom 5 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of InternLM2 Chat 20B, out of 828 with a score, then more from Shanghai AI Laboratory (InternLM).

#modelscorewhereRAMreleased
607speechless-coding-7b-16k-tora uukuguy41±1local~16GB2023-10
608DeepSeek-Coder 33B Base DeepSeek41±1local~22GB2023-10
609InternLM2 Chat 20B Shanghai AI Laboratory (InternLM)41±1local~14GB2024-01
610DeepSeek LLM 67B Chat DeepSeek41±1local~31GB2023-11
611Llama 2 70B (base) Meta41±1local~32GB2023-07
more from Shanghai AI Laboratory (InternLM)
446InternLM2.5 7B Chat Shanghai AI Laboratory (InternLM)49±2local~6.1GB2024-06
486InternLM2.5 7B Chat 1M Shanghai AI Laboratory (InternLM)47±4local~6.4GB2024-06
520InternLM2.5 20B Chat Shanghai AI Laboratory (InternLM)46±2local~14GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #310 of 393 * · 73% of its score · 2 tests

Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled18.8% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 49/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%typical
Arena-Hard (v0.1, GPT-4-1106 judge)24.4% ✎▂▁▁▅█▅▄▃▃▅▃▁ beats 23/60medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp
other tests3 not in a task · 26% of its score
testresultvs the others in its rundifficultycountswhy
CPTUB average (SpeakLeash, 0-5 judge scale)43.0% ✎▁▂▃▂▃█▃▆▅▄▂▃ beats 10/95easy · avg 66%▇▇▇▇▇ 13%at its level
Polish EQ-Bench v2 (SpeakLeash)36.5% ✎▁··▁▁▂▃▆▅▆█▆ beats 10/70medium · avg 64%▇▇▇▇ 10%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)70.6% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 169/276medium · avg 73%▇ 3.6%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 InternLM2 Chat 20B · needs ~12 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/internlm2-chat-20b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/internlm2-chat-20b-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 InternLM2 Chat 20B · needs ~12 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/internlm2-chat-20b-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 InternLM2 Chat 20B · needs ~12 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/internlm2-chat-20b-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~39.72 GB · from huggingface.co/internlm (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='internlm/internlm2-chat-20b', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/internlm ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 45%, Arena-Hard-Auto v0.1 leaderbo… 28%, SpeakLeash CPTUB (Complex Pol… 13% 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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%Apache-2.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)1▇▇▇▇▇▇▇▇ 28%Apache-2.0
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇▇▇ 13%MIT
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇ 10%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 4%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 40.9

$ 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