whatmodel.sh / Yi 1.5 9B Chat

Yi 1.5 9B Chat

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

Yi 1.5 9B Chat is an open-weights language model from 01.AI, released May 2024. Its published size is 8.83B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo 01-ai/Yi-1.5-9B-Chat @1a0fc69: licence tag apache-2.0. 8,829,407,232 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-10). Ollama tags yi:9b-chat-v1.5-q4_K_M, yi:9b-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.

44.2±0.8#452 of 719 LLMsfrom 15 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of Yi 1.5 9B Chat, out of 828 with a score, then more from 01.AI.

#modelscorewhereRAMreleased
539LLaVA-OneVision Qwen2 72B (ov-sft) LLaVA (lmms-lab)44±3local~155GB2024-08
540Phi-3-mini-4k-instruct (June 2024 update) Microsoft44±1local~3.7GB2024-06
541Yi 1.5 9B Chat 01.AI44±1local~6.8GB2024-05
542Command R7B (12-2024) Cohere44±1local~6.2GB2024-12
543Qwen2-Audio 7B Instruct Alibaba44±3local~6.5GB2024-07
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

coding▁▁▁▃▆██▇▆▄▃▁ #274 of 458 · 21% of its score · 5 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CRUXEval (ZeroEval, 800 problems)44.8% ✎▁▂▆▃▆█▆▃▂·▁▁ beats 9/47medium · avg 61%▇▇▇▇▇▇▇ 17%sharp · at its level
CodeReviewQA: solution identification (hard), invariant accuracy58.9% ✎▃··▁▂▂▃▂█▃▄▂ beats 33/47medium · avg 54%▇ 1.5%sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy43.2% ✎█▂▁▁▂▂▂▃▅▅▅▇ beats 33/47medium · avg 36%▇ 1.4%sharp · noisy
CodeReviewQA: automated code refinement, exact match rate30.7% ✎▁▁▁▁▁▁▂▂▃█▅▄ beats 22/47hard · avg 33%▇ 1.1%typical
CodeReviewQA: change type recognition, invariant accuracy78.6% ✎▁▁▁······▁▃█ beats 42/47easy · avg 67%▇ 0.0%blunt · at its level · noisy
math▁▂▃▅▆▅▄█▄▁▁▁ #337 of 398 * · 17% of its score · 2 tests

Beats GPT-3.5 Turbo (0125), DBRX Instruct, Command R Plus (04-2024) here, though they rank higher overall. Trails Qwen3 0.6B, Gemma 7B (base), LFM2 700M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K (ZeroEval, zero-shot)76.4% ✎▁▄·▁▄█▅▅▅███ beats 7/43very easy · avg 89%▇▇▇▇▇ 12%sharp
MATH Level 5 (ZeroEval, 721 problems)20.0% ✎▁▁▁▆█▂▇▇▄··▂ beats 8/38hard · avg 34%▇▇ 5.5%sharp
other tests8 not in a task · 61% of its score
testresultvs the others in its rundifficultycountswhy
MMLU-Redux (ZeroEval, 2,778 questions)65.0% ✎▁·▁▁▄▄▄▅█▄▂▁ beats 8/53easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇ 30%at its level
BigCodeBench (Complete)42.2% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 33/58medium · avg 50%▇▇▇ 7.0%at its level
BigCodeBench (Instruct)34.3% ✎▃▂·▆▆██▆▅▃▃▃ beats 15/33medium · avg 41%▇▇▇ 6.9%at its level
WildBench v2 WB-Score (task macro)38.6654 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 25/52avg 45.199 WB-Score▇▇▇ 6.7%sharp
ZebraLogic (ZeroEval, 1,000 puzzles)2.3% ✎▃▁▃▆██▁▁·▁▁▁ beats 0/57hard · avg 18%▇▇ 4.9%sharp
Polish EQ-Bench v2 (SpeakLeash)48.8% ✎▁··▁▁▂▂▆▅▆█▆ beats 23/70medium · avg 64%▇ 3.5%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)67.9% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 143/276medium · avg 73%▇ 1.3%at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)95.1% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 61/140very easy · avg 94%▇ 0.5%blunt · maxed out · 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 9B Chat · needs ~5.3 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Yi-1.5-9B-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-1.5-9B-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 9B Chat · needs ~5.3 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-1.5-9B-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 9B Chat · needs ~5.8 GB · from ollama.com
    chat in the terminal
    ollama run yi:9b-chat-v1.5-q4_K_M

MLX (Mac)

  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 9B Chat · needs ~5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Yi-1.5-9B-Chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Yi-1.5-9B-Chat-4bit

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

$ how the score was worked out · WildEval ZeroEval published r… 70%, BigCodeBench paper (Zhuo et a… 14%, WildBench v2 leaderboard data… 7% and 4 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
WildEval ZeroEval published results5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%Apache-2.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇▇▇ 14%CC BY 4.0
WildBench v2 leaderboard data (Ai2)1▇▇ 7%Apache-2.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇ 4%CC-BY-4.0
SpeakLeash Polish EQ-Bench leaderboard1▇ 4%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 0%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 44.2

$ 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