whatmodel.sh / Qwen2 7B Instruct

Qwen2 7B Instruct

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

Qwen2 7B Instruct is an open-weights language model from Alibaba, released June 2024. Its published size is 7.62B parameters and a 131k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo Qwen/Qwen2-7B-Instruct @f2826a0: licence tag apache-2.0. 7,615,616,512 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). Ollama tags qwen2:7b-instruct-q4_K_M, qwen2:7b-instruct-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.

44.0±0.6#461 of 719 LLMsfrom 22 benchmark results across 10 sources

$ how it compares

The LLMs ranked either side of Qwen2 7B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
548Qwen1.5 32B Chat Alibaba44±1local~22GB2024-04
549Granite 20B Code Instruct (8K) IBM44±1local~14GB2024-04
550Qwen2 7B Instruct Alibaba44±1local~6GB2024-06
551Falcon3 7B Instruct TII44±3local~5.9GB2024-11
552Xwin-LM 70B v0.1 Xwin-LM44±1local~28GB2023-09
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #279 of 300 * · 0.8% of its score · 1 test

Beats Bielik 11B v2.3 Instruct, GLM-4 9B Chat, Command R (08-2024) here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v341.3% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 17/114medium · avg 52%▇ 0.8%blunt · at its level
coding▁▁▁▃▆██▇▆▄▃▁ #344 of 458 * · 11% 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, OpenChat 3.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CRUXEval (ZeroEval, 800 problems)37.9% ✎▁▂▆▃▆█▆▃▂·▁▁ beats 4/47medium · avg 61%▇▇▇▇ 11%sharp · at its level
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #274 of 393 * · 2.8% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, Gemma 4 E4B here, though they rank higher overall. Trails Flan-T5 XXL, EXAONE 3.5 2.4B Instruct, LFM2 1.2B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arabic IFEval prompt-level (Inception)38.1% ✎▁·▁▁▂▁▄▄▆▄█▄ beats 22/38medium · avg 49%▇ 2.8%sharp · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #330 of 398 · 28% of its score · 5 tests

Beats GPT-3.5 Turbo (0125), Qwen2-VL 7B Instruct, DBRX Instruct here, though they rank higher overall. Trails Qwen3 0.6B, Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab +185.7% ✎▄···█▄▄·▄·▄█ beats 3/8very easy · avg 92%▇▇▇ 8.6%sharp · several runs
GSM8K (ZeroEval, zero-shot)80.1% ✎▁▄·▁▄█▅▅▅███ beats 10/43very easy · avg 89%▇▇▇ 7.5%sharp
MATH (subset unspecified) lab +152.9% ✎▃····▃·▅·▅·█ beats 1/8easy · avg 76%▇▇ 4.7%at its level · several runs
MATH Level 5 (ZeroEval, 721 problems)23.9% ✎▁▁▁▆█▂▇▇▄··▂ beats 12/38hard · avg 34%▇ 3.4%sharp
Minerva MATH lab19.5% ✎▃·····▃··█▅▅ beats 1/8medium · avg 37%▇ 3.4%at its level
other tests12 not in a task · 58% of its score
testresultvs the others in its rundifficultycountswhy
MMLU-Redux (ZeroEval, 2,778 questions)66.9% ✎▁·▁▁▄▄▄▅█▄▂▁ beats 10/53easy · avg 77%▇▇▇▇▇▇▇▇ 19%at its level
LiveBench 2024-07-2626.6% ✎▁▁▁▂▂▃▃█▆▃▅▃ beats 19/61medium · avg 41%▇▇▇▇▇ 14%at its level
BigCodeBench (Complete) lab40.7% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 29/58medium · avg 50%▇▇ 4.4%at its level
BigCodeBench (Instruct) lab28.0% ✎▃▂·▆▆██▆▅▃▃▃ beats 3/33medium · avg 41%▇▇ 4.3%at its level
BIG-Bench Hard65.0% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 75/129easy · avg 75%▇ 3.3%sharp · at its level · small run
ZebraLogic (ZeroEval, 1,000 puzzles)8.4% ✎▁▁▃▆██▁▁·▁▁▁ beats 5/57hard · avg 18%▇ 3.0%sharp
MMLU70.8% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 117/183easy · avg 78%▇ 2.7%at its level
Polish EQ-Bench v2 (SpeakLeash)53.7% ✎▁··▁▁▂▂▆▅▆█▆ beats 28/70medium · avg 64%▇ 2.2%at its level
4 more tests
testresultvs the others in its rundifficultycountswhy
GPQA (subset unspecified)38.4% ✎▂▁▂▂▄▃▆▃▅█▄▃ beats 34/104hard · avg 40%▇ 1.6%sharp
Open Persian LLM Leaderboard v2 average (21 tasks)50.0% ✎▂▄▂▃█▄▃▆▃▅▂▂ beats 28/81medium · avg 58%▇ 1.6%blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)72.1% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 192/276medium · avg 73%▇ 0.8%at its level · noisy
CMMLU80.9% ✎▅·▅····█▃▅█▅ beats 7/14easy · avg 75%▇ 0.8%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 Qwen2 7B Instruct · needs ~4.7 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen2-7B-Instruct-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf Qwen/Qwen2-7B-Instruct-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 Qwen2 7B Instruct · needs ~4.7 GB · from huggingface.co/Qwen (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/Qwen/Qwen2-7B-Instruct-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 Qwen2 7B Instruct · needs ~5.07 GB · from ollama.com
    chat in the terminal
    ollama run qwen2:7b-instruct-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 Qwen2 7B Instruct · needs ~4.3 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen2-7B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen2-7B-Instruct-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · WildEval ZeroEval published r… 44%, InternLM GitHub repository mo… 14%, LiveBench model judgments (HF… 14% and 7 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▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%Apache-2.0
InternLM GitHub repository model cards (Shanghai AI Laboratory)6▇▇▇▇ 14%Apache-2.0
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇ 14%Apache-2.0 (stated in the LiveBench datasheet)
Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card) · lab-reported3▇▇▇ 11%Factual vendor-reported score (not licensed content)
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4 · lab-reported2▇▇▇ 9%CC BY 4.0
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)1▇ 3%Apache-2.0
SpeakLeash Polish EQ-Bench leaderboard1▇ 2%Apache-2.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)1▇ 2%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
Berkeley Function Calling Leaderboard result archive1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 44.0

$ 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