whatmodel.sh / OpenChat 3.5

OpenChat 3.5

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

OpenChat 3.5 is an open-weights language model from OpenChat, released October 2023. Its published size is 7B parameters and a 8k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'openchat-3.5' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'openchat-3.5' as 'OpenChat-3.5' (OpenChat, Apache-2.0), linking https://huggingface.co/openchat/openchat_3.5. Maker repo openchat/openchat_3.5 @0fc98e3: licence tag apache-2.0. Parameters: card table '# Param 7B'. Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-30).

41.3±1.5#511 of 719 LLMsfrom 7 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of OpenChat 3.5, out of 828 with a score, then more from OpenChat.

#modelscorewhereRAMreleased
601Snowflake Arctic Instruct Snowflake41±2local~1007GB2024-04
602Phi-3-vision-128k-instruct Microsoft41±2local~10GB2024-05
603OpenChat 3.5 OpenChat41±2local~6.1GB2023-10
604InternVL2-4B Shanghai AI Laboratory (OpenGVLab)41±2local~10GB2024-07
605Qwen1.5 14B Chat Alibaba41±1local~11GB2024-02
more from OpenChat
505OpenChat 3.5 0106 OpenChat46±1local~6.1GB2024-01
518OpenChat 3.5 0106 Gemma OpenChat46±3local~6.9GB2024-03

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #341 of 458 * · 18% of its score · 1 test

Beats LFM2.5 2.6B, LFM2.5 8B-A1B, Qwen3-VL 2B Thinking here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval lab55.5% ✎▁▁▁▁▁▃▅▅█▃▂▁ beats 92/190easy · avg 77%▇▇▇▇▇▇▇ 18%sharp · at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #321 of 393 * · 39% 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
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1101.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 47/95avg 1201▇▇▇▇▇▇▇▇ 19%blunt
LMArena (text)1183.0 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 59/379avg 1268▇▇▇▇▇▇▇▇ 19%blunt
math█··········█ #1 of 2 * · 12% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
GSM8K lab77.3% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 87/146very easy · avg 89%▇▇▇▇▇ 12%sharp · at its level · small run
other tests3 not in a task · 31% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab63.5% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 72/129easy · avg 80%▇▇▇▇▇ 13%sharp · at its level · small run
MMLU lab64.3% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 81/183easy · avg 77%▇▇▇▇ 9.1%at its level · small run
EQ-Bench v1 (60 questions, paper run)37.1% ✎▂··▄·▂▆▄▂█·▂ beats 5/14medium · avg 57%▇▇▇ 8.7%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 OpenChat 3.5 · needs ~4.4 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/openchat_3.5-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/openchat_3.5-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 OpenChat 3.5 · needs ~4.4 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/openchat_3.5-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 OpenChat 3.5 · needs ~4.7 GB · from ollama.com
    chat in the terminal
    ollama run openchat:7b-v3.5-q4_K_M

Official weights and documentation: huggingface.co/openchat ↗

$ how the score was worked out · OpenChat 3.5 model card (open… 52%, Polyrating: A Cost-Effective… 19%, LMArena leaderboard dataset 19% 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
OpenChat 3.5 model card (openchat/openchat_3.5) · lab-reported4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇ 19%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇ 19%CC BY 4.0
EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs1▇▇▇ 9%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 41.3

$ 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