whatmodel.sh / Code Llama 70B Instruct

Code Llama 70B Instruct

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

Code Llama 70B Instruct is an open-weights language model from Meta, released January 2024. Its published size is 69B parameters and a 16k-token context window. Licence: llama2.

Catalogue identity notes

Arena entry 'codellama-70b-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'codellama-70b-instruct' as 'CodeLlama-70B-instruct' (Meta, Llama 2 Community), linking https://huggingface.co/codellama/CodeLlama-70b-hf. Maker repo codellama/CodeLlama-70b-Instruct-hf @397cae9: 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). LMArena's table links codellama/CodeLlama-70b-hf (the base repo) but labels the entry 'CodeLlama-70B-instruct'; the instruct repo is used here.

46.1±0.6#417 of 719 LLMsfrom 13 benchmark results across 7 sources

$ how it compares

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

#modelscorewhereRAMreleased
495GPT-3.5 Turbo (1106) OpenAI46±1comparison only2023-11
496Cogito v1 Preview Llama 3B Deep Cogito46±4local~3.4GB2025-03
497Code Llama 70B Instruct Meta46±1local~28GB2024-01
498Hermes 2 Pro Llama 3 8B Nous Research46±3local~6.6GB2024-04
499Llama 3 70B (base) Meta46±2local~43GB2024-04
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▁▁▁▃▆██▇▆▄▃▁ #303 of 458 · 78% of its score · 6 tests

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3-VL 30B-A3B Instruct here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Yi 1.5 9B Chat here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +272.0% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 63/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%sharp · at its level · several runs
HumanEval+65.9% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 62/99easy · avg 74%▇▇▇▇▇▇▇ 19%sharp · at its level
HumanEvalSynthesize (HumanEvalPack, 6-language average)58.9% ✎▁·▂▁▂▆▅█▄▄▃▂ beats 33/35medium · avg 64%▇▇ 5.2%at its level
HumanEvalExplain (HumanEvalPack, 6-language average)41.1% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 32/35medium · avg 49%▇▇ 4.0%at its level
HumanEvalFix (HumanEvalPack, 6-language average)53.0% ✎▁·▁▁▄██▄█▁▅▅ beats 34/35medium · avg 56%▇▇ 3.9%sharp · at its level
MBPP lab62.2% ✎▃▃▃█··▃▅··▅▃ beats 9/11easy · avg 73%▇ 3.3%at its level
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #369 of 393 * · 5.7% of its score · 2 tests

Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1039.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 22/95avg 1201▇ 2.9%blunt
LMArena (text)1119.1 ✎▁▁▁▃▃▃▃▆▆▇█▃ beats 22/379avg 1268▇ 2.8%blunt
other tests3 not in a task · 16% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)47.7% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 33/42medium · avg 55%▇▇▇▇ 8.9%at its level
BigCodeBench (Instruct)40.5% ✎▃▂·▆▆██▆▅▃▃▃ beats 26/33medium · avg 41%▇ 3.4%at its level
BigCodeBench (Complete)48.9% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 49/58medium · avg 50%▇ 3.4%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 Instruct · needs ~41.4 GB · from huggingface.co/second-state
    chat in the terminal
    llama cli -hf second-state/CodeLlama-70b-Instruct-hf-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf second-state/CodeLlama-70b-Instruct-hf-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 Instruct · needs ~41.4 GB · from huggingface.co/second-state

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/second-state/CodeLlama-70b-Instruct-hf-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 Instruct · needs ~41.9 GB · from ollama.com
    chat in the terminal
    ollama run codellama:70b-instruct-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 Instruct · needs ~39.2 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX

Weights and documentation: huggingface.co/codellama ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 42%, Top Leaderboard Ranking = Top… 22%, Granite Code Models: A Family… 13% 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 runs2▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇ 22%CC BY 4.0
Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs3▇▇▇▇ 13%CC BY 4.0
Code Llama: Open Foundation Models for Code — authors' own runs · lab-reported2▇▇▇ 11%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇ 7%CC BY 4.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇ 3%CC-BY-4.0
LMArena leaderboard dataset1▇ 3%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 46.1

$ 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