whatmodel.sh / Yi 1.5 6B Chat

Yi 1.5 6B Chat

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

Yi 1.5 6B Chat is an open-weights language model from 01.AI, released May 2024. Its published size is 6.06B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo 01-ai/Yi-1.5-6B-Chat @771924d: licence tag apache-2.0. 6,061,035,520 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-11). Ollama tags yi:6b-chat-v1.5-q4_K_M, yi:6b-chat-v1.5-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.

36.6±1.7#583 of 719 LLMsfrom 6 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Yi 1.5 6B Chat, out of 828 with a score, then more from 01.AI.

#modelscorewhereRAMreleased
674Code Llama 13B (base) Meta37±1local~9.2GB2023-08
675Qwen1.5 7B Chat Alibaba37±1local~6.5GB2024-02
676Yi 1.5 6B Chat 01.AI37±2local~5.1GB2024-05
677Falcon3 3B Instruct TII37±3local~3.4GB2024-12
678Zephyr 7B alpha Hugging Face36±1local~6.1GB2023-10
more from 01.AI
308Yi-Lightning 01.AI55±1api price unknown2024-10
373Yi-Large Preview 01.AI52±1comparison only2024-05
396Yi-Large 01.AI51±1comparison only2024-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests6 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
WildBench v2 WB-Score (task macro)23.3181 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 5/52avg 45.199 WB-Score▇▇▇▇▇▇▇▇▇▇▇ 28%sharp
BigCodeBench (Complete)33.8% ✎▂▁▁▄▃▅▇█▆▂▂▂ beats 14/58medium · avg 50%▇▇▇▇▇▇▇▇▇▇ 26%at its level
BigCodeBench (Instruct)25.5% ✎▃▃·▆▆██▆▅▃▃▃ beats 2/33medium · avg 41%▇▇▇▇▇▇▇▇▇ 24%typical
Polish EQ-Bench v2 (SpeakLeash)5.2% ✎▃··▁▁▂▂▆▅▆█▆ beats 0/70medium · avg 64%▇▇▇▇▇ 14%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)62.6% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 98/276medium · avg 73%▇▇ 5.0%at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)92.1% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 37/140very easy · avg 94%▇ 2.6%blunt · 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 Yi 1.5 6B Chat · needs ~3.7 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Yi-1.5-6B-Chat-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Yi-1.5-6B-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 Yi 1.5 6B Chat · needs ~3.7 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Yi-1.5-6B-Chat-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 Yi 1.5 6B Chat · needs ~4.14 GB · from ollama.com
    chat in the terminal
    ollama run yi:6b-chat-v1.5-q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Yi 1.5 6B Chat · needs ~3.4 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Yi-1.5-6B-Chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Yi-1.5-6B-Chat-4bit

Official weights and documentation: huggingface.co/01-ai ↗

$ how the score was worked out · BigCodeBench paper (Zhuo et a… 49%, WildBench v2 leaderboard data… 28%, SpeakLeash Polish EQ-Bench le… 14% 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
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%CC BY 4.0
WildBench v2 leaderboard data (Ai2)1▇▇▇▇▇▇▇▇ 28%Apache-2.0
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇▇ 14%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 5%Apache-2.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 3%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 36.6

$ 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