whatmodel.sh / Code Llama 70B Python

Code Llama 70B Python

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

Code Llama 70B Python is an open-weights language model from Meta, released January 2024. Its published size is 68.98B parameters and a 16k-token context window. Licence: llama2.

Catalogue identity notes

Maker repo codellama/CodeLlama-70b-Python-hf @e037619: licence tag llama2. 68,976,910,336 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-29). Python-specialised Code Llama 70B; not instruction-tuned. Ollama tags codellama:70b-python-q4_K_M, codellama:70b-python-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

43.6±1.0#473 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Code Llama 70B Python, out of 828 with a score, then more from Meta.

#modelscorewhereRAMreleased
560Ministral 8B (2410) Mistral44±1local~6.2GB2024-10
561Granite 3.2 8B Instruct IBM44±1local~6.6GB2025-02
562Code Llama 70B Python Meta44±1local~28GB2024-01
563Llama 3.1 8B (base) Meta44±3local~6.2GB2024-07
564LFM2.5 1.2B Instruct Liquid AI44±2local~2.2GB2026-01
more from Meta
24Muse Spark 1.3 Meta77±1api $2.00/M2026-09
40Muse Spark 1.2 Meta75±1api $2.00/M2026-08
43Muse Spark 1.1 Meta75±1api $2.00/M2026-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #334 of 458 · 74% of its score · 2 tests

Beats GLM-4.7-Flash, LFM2.5 2.6B, LFM2.5 8B-A1B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +160.4% ✎▁█▄▅▇█·▄▇▅▄▄ beats 25/42easy · avg 78%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%sharp · at its level · several runs
MBPP lab65.6% ✎▃▃▃█··▃▅··▅▃ beats 11/11easy · avg 73%▇▇▇▇ 10%at its level
other tests1 not in a task · 25% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)40.1% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 26/42medium · avg 55%▇▇▇▇▇▇▇▇▇▇ 25%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 Code Llama 70B Python · needs ~41.4 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/CodeLlama-70B-Python-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/CodeLlama-70B-Python-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 Code Llama 70B Python · needs ~41.4 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/CodeLlama-70B-Python-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 Code Llama 70B Python · needs ~41 GB · from ollama.com
    chat in the terminal
    ollama run codellama:70b-python-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 Code Llama 70B Python · needs ~39.2 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/CodeLlama-70b-Python-hf-4bit-MLX
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/CodeLlama-70b-Python-hf-4bit-MLX

Weights and documentation: huggingface.co/codellama ↗

$ how the score was worked out · Top Leaderboard Ranking = Top… 67%, Code Llama: Open Foundation M… 33%

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
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%CC BY 4.0
Code Llama: Open Foundation Models for Code — authors' own runs · lab-reported2▇▇▇▇▇▇▇▇▇▇ 33%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 43.6

$ 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