whatmodel.sh / Code Llama 13B (base)

Code Llama 13B (base)

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

Code Llama 13B (base) is an open-weights language model from Meta, released August 2023. Its published size is 13.02B parameters and a 16k-token context window. Licence: llama2.

Catalogue identity notes

Maker repo codellama/CodeLlama-13b-hf @8da65ff: licence tag llama2. 13,016,028,160 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-08: month the maker's Hugging Face repo was created (createdAt 2023-08-24). Pretrained Code Llama; not the Python or Instruct variant. Ollama tags codellama:13b-code-q4_K_M, codellama:13b-code-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

36.7±0.5#581 of 719 LLMsfrom 23 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of Code Llama 13B (base), out of 828 with a score, then more from Meta.

#modelscorewhereRAMreleased
672Code Llama 7B Python Meta37±1local~5.8GB2023-08
673Dolphin 2.2.1 Mistral 7B Cognitive Computations37±2local~6.1GB2023-10
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
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▁▁▁▃▆██▇▆▄▃▁ #399 of 458 · 88% of its score · 11 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, Code Llama 7B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +242.7% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 25/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp · at its level · several runs
HumanEval+38.4% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 28/99easy · avg 74%▇▇▇▇▇▇▇ 17%sharp · at its level
MBPP +230.6% ✎█·▅▃▃▃▅▃▃▅·▅ beats 2/15easy · avg 73%▇▇▇▇ 9.0%at its level · several runs
HumanEvalSynthesize (HumanEvalPack, 6-language average)37.8% ✎▁·▂▁▂▆▅█▄▄▁▂ beats 15/35medium · avg 64%▇▇ 4.5%at its level
MBPP+52.6% ✎▁···▁▁▂▅▇█▆▂ beats 23/75easy · avg 68%▇ 3.2%at its level
CRUXEval-I lab +142.5% ✎▁··▁▅▂█▇▁··▁ beats 14/22medium · avg 59%▇ 3.0%at its level · several runs
DS-100025.1% ✎▄▄·▄██▄█·█·▄ beats 7/12medium · avg 52%▇ 2.7%at its level
CRUXEval-O lab +139.7% ✎▁·▂▃▁█▁▂···▁ beats 9/22medium · avg 55%▇ 2.6%blunt · at its level · several runs
3 more tests
testresultvs the others in its rundifficultycountswhy
HumanEvalExplain (HumanEvalPack, 6-language average)15.0% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 10/35medium · avg 49%▇ 2.6%typical
HumanEvalFix (HumanEvalPack, 6-language average)9.5% ✎▁·▁▁▄██▄█▁▅▅ beats 5/35medium · avg 56%▇ 2.3%sharp
Tulu 2: CodexEval pass@1069.8% ✎▃▃▃·▆▃▃█▃▂▂▅ beats 18/25very easy · avg 86%▇ 2.2%sharp · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #363 of 398 * · 3.2% of its score · 1 test

Beats Yi 34B Chat, Llama 3 8B Instruct, Command R (03-2024) here, though they rank higher overall. Trails Gemma 3 1B, OLMo 2 1B Instruct (0425), Stable Code 3B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K +122.0% ✎▆▂▅█▅▅▃▆···▂ beats 5/25easy · avg 75%▇ 3.2%sharp · at its level · several runs
other tests4 not in a task · 8.2% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard49.5% ✎▁·····▂█▂▅·▁ beats 13/25easy · avg 77%▇ 3.7%sharp · at its level
BigCodeBench (Complete)32.0% ✎▂▁▁▄▃▅▇█▆▂▂▂ beats 13/58medium · avg 50%▇ 2.7%at its level
MMLU37.5% ✎▁▃▃▃▄█▄▁█··▁ beats 1/25easy · avg 74%▇ 1.4%at its level
Tulu 2: TyDiQA gold passage, 1-shot F152.1% ✎▂··▁▃▂▂▂█▅▁▂ beats 15/25medium · avg 61%▇ 0.5%blunt · 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 13B (base) · needs ~7.9 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/CodeLlama-13B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/CodeLlama-13B-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 13B (base) · needs ~7.9 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/CodeLlama-13B-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 13B (base) · needs ~7.9 GB · from ollama.com
    chat in the terminal
    ollama run codellama:13b-code-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 Code Llama 13B (base) · needs ~7.3 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/CodeLlama-13b-hf-4bit-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/CodeLlama-13b-hf-4bit-mlx

Weights and documentation: huggingface.co/codellama ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 45%, StarCoder 2 and The Stack v2:… 16%, Granite Code Models: A Family… 16% 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
EvalPlus / EvalPerf published evaluation runs3▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%Apache-2.0
StarCoder 2 and The Stack v2: The Next Generation — authors' own runs4▇▇▇▇▇ 16%CC BY-SA 4.0
Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs6▇▇▇▇▇ 16%CC BY 4.0
Code Llama: Open Foundation Models for Code — authors' own runs · lab-reported2▇▇▇ 10%CC BY 4.0
Tulu 2 — base and instruction-tuned evaluations5▇▇▇ 9%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇ 3%CC BY 4.0
CRUXEval published evaluation results (authors' generations and scores) · lab-reported2▇ 2%MIT
prior · pull toward the middle▇ 0%
weighted average= 36.7

$ 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