whatmodel.sh / CodeGemma 7B (v1.0)

CodeGemma 7B (v1.0)

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

CodeGemma 7B (v1.0) is an open-weights language model from Google, released March 2024. Its published size is 8.54B parameters. Licence: gemma.

Catalogue identity notes

Maker repo google/codegemma-7b @2ec9700: licence tag gemma. 8,537,680,896 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-03: month the maker's Hugging Face repo was created (createdAt 2024-03-21). Pretrained CodeGemma 7B; not the instruction-tuned model. Ollama tags codegemma:7b-code-q4_K_M, codegemma:7b-code-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

38.2±0.6#559 of 719 LLMsfrom 14 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of CodeGemma 7B (v1.0), out of 828 with a score, then more from Google.

#modelscorewhereRAMreleased
649Qwen-14B-Chat Alibaba38±1local~11GB2023-09
650Falcon-180B-Chat TII38±2local~115GB2023-09
651CodeGemma 7B (v1.0) Google38±1local~7.1GB2024-03
652Code Llama 13B Python Meta38±1local~9.8GB2023-08
653Tulu 2 13B Allen Institute for AI38±2local~9.8GB2023-11
more from Google
9Gemini 4 Argon (limited preview) Google82±1limited preview2026-09
23Gemini 3.8 Flash Google77±1api $1.50/M2026-09
32Gemini 3.7 Flash Google76±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #393 of 458 · 94% of its score · 9 tests

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +144.5% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 28/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp · at its level · several runs
HumanEval+41.5% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 32/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇ 24%sharp · at its level
HumanEvalSynthesize (HumanEvalPack, 6-language average)41.5% ✎▁·▂▁▂▆▅█▄▄▁▂ beats 20/35medium · avg 64%▇▇▇ 6.4%at its level
MBPP +153.0% ✎█·▅▃▃▃▅▃▃▅·▅ beats 15/15easy · avg 70%▇▇ 5.6%at its level · several runs
MBPP+52.4% ✎▁···▁▁▂▅▇█▆▂ beats 22/75easy · avg 68%▇▇ 4.5%at its level
HumanEvalExplain (HumanEvalPack, 6-language average)12.4% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 4/35medium · avg 49%▇▇ 3.8%typical
HumanEvalFix (HumanEvalPack, 6-language average)10.1% ✎▁·▁▁▄██▄█▁▅▅ beats 6/35medium · avg 56%▇ 3.5%sharp
CRUXEval-I42.6% ✎▃▅█▃▃▅·▃▃▅·▅ beats 12/15medium · avg 59%▇ 2.8%at its level
1 more test
testresultvs the others in its rundifficultycountswhy
CRUXEval-O43.9% ✎▃·▃██▅▃·▃▃▅▃ beats 13/15medium · avg 55%▇ 2.3%blunt · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #294 of 398 * · 2.5% of its score · 2 tests

Beats GPT-4 (0613), Athene-70B, Gemma 2 27B IT here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH21.8% ✎▃·▃····▃···█ beats 4/5medium · avg 40%▇ 1.3%noisy
GSM8K49.0% ✎▄··▄···▄··█▄ beats 3/5easy · avg 77%▇ 1.2%sharp · at its level · noisy
other tests1 not in a task · 3.8% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Complete)37.3% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 20/58medium · avg 50%▇▇ 3.8%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 CodeGemma 7B (v1.0) · needs ~5.3 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/codegemma-7b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/codegemma-7b-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 CodeGemma 7B (v1.0) · 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/codegemma-7b-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 CodeGemma 7B (v1.0) · needs ~5.3 GB · from ollama.com
    chat in the terminal
    ollama run codegemma:7b-code-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 CodeGemma 7B (v1.0) · needs ~5.9 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/codegemma-7b-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/codegemma-7b-4bit

Official weights and documentation: huggingface.co/google ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 64%, Granite Code Models: A Family… 25%, CodeGemma: Open Code Models B… 7% 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
EvalPlus / EvalPerf published evaluation runs3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%Apache-2.0
Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs8▇▇▇▇▇▇▇ 25%CC BY 4.0
CodeGemma: Open Code Models Based on Gemma — authors' own runs · lab-reported2▇▇ 7%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇ 4%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 38.2

$ 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