Ollama · codellama

<img src="https://github.com/jmorganca/ollama/assets/3325447/286e4e13-0b2b-43a4-9b07-23a50d3a3d33" width="360" /> Code Llama is a model for generating and discussing code, built on top of [Llama 2](h…

ollama/codellama

<img src="https://github.com/jmorganca/ollama/assets/3325447/286e4e13-0b2b-43a4-9b07-23a50d3a3d33" width="360" />

Code Llama is a model for generating and discussing code, built on top of [Llama 2](https://ollama.ai/library/llama2). It's designed to make workflows faster and efficient for developers and make it easier for people to learn how to code. It can generate both code and natural language about code. Code Llama supports many of the most popular programming languages used today, including Python, C++, Java, PHP, Typescript (Javascript), C#, Bash and more.

## Parameter counts

| Parameter Count | | | | --------------- | ------------------------------ | -------------------------- | | 7 billion | [View](/library/codellama:7b) | `ollama run codellama:7b` | | 13 billion | [View](/library/codellama:13b) | `ollama run codellama:13b` | | 34 billion | [View](/library/codellama:34b) | `ollama run codellama:34b` | | 70 billion | [View](/library/codellama:70b) | `ollama run codellama:70b` |

## Usage

### CLI

``` ollama run codellama "Write me a function that outputs the fibonacci sequence" ```

### API

``` curl -X POST http://localhost:11434/api/generate -d '{ "model": "codellama", "prompt": "Write me a function that outputs the fibonacci sequence" }' ```

## Variations

| | | | ---------- | -------------------------------------------------------------------------------------- | | `instruct` | Fine-tuned to generate helpful and safe answers in natural language | | `python` | A specialized variation of Code Llama further fine-tuned on 100B tokens of Python code | | `code` | Base model for code completion |

## Example prompts

### Ask questions

``` ollama run codellama:7b-instruct 'You are an expert programmer that writes simple, concise code and explanations. Write a python function to generate the nth fibonacci number.' ```

### Fill-in-the-middle (FIM) or infill

``` ollama run codellama:7b-code '<PRE> def compute_gcd(x, y): <SUF>return result <MID>' ```

Fill-in-the-middle (FIM) is a special prompt format supported by the code completion model can complete code between two already written code blocks. Code Llama expects a specific format for infilling code:

``` <PRE> {prefix} <SUF>{suffix} <MID> ```

`<PRE>`, `<SUF>` and `<MID>` are special tokens that guide the model.

### Code review

``` ollama run codellama ' Where is the bug in this code?

def fib(n): if n <= 0: return n else: return fib(n-1) + fib(n-2) ' ```

### Writing tests

``` ollama run codellama "write a unit test for this function: $(cat example.py)" ```

### Code completion

``` ollama run codellama:7b-code '# A simple python function to remove whitespace from a string:' ```

## More information

- [How to prompt Code Llama](https://ollama.ai/blog/how-to-prompt-code-llama) - [Whitepaper](https://arxiv.org/abs/2308.12950) - [CodeLlama GitHub](https://github.com/facebookresearch/codellama) - [Hugging Face](https://huggingface.co/codellama)

Specifications & capabilities

Published model ID
codellama

Deployments & artifacts

81–100 / 199

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q8_0
context window
16000
context window is approximate
true
artifact size bytes
35856052543
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q4_0
context window
16000
context window is approximate
true
artifact size bytes
19052053345
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
F16
context window
16000
context window is approximate
true
artifact size bytes
67490284353
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q2_K
context window
16000
context window is approximate
true
artifact size bytes
14210679649
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
16000
context window is approximate
true
artifact size bytes
17771529057
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q3_K_M
context window
16000
context window is approximate
true
artifact size bytes
16283599713
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q3_K_S
context window
16000
context window is approximate
true
artifact size bytes
14605353825
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q4_0
context window
16000
context window is approximate
true
artifact size bytes
19052053345
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q4_1
context window
16000
context window is approximate
true
artifact size bytes
21144617825
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
16000
context window is approximate
true
artifact size bytes
20219904865
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
16000
context window is approximate
true
artifact size bytes
19146425185
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q5_0
context window
16000
context window is approximate
true
artifact size bytes
23237182305
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q5_1
context window
16000
context window is approximate
true
artifact size bytes
25329746785
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
16000
context window is approximate
true
artifact size bytes
23838802785
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
16000
context window is approximate
true
artifact size bytes
23237182305
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q6_K
context window
16000
context window is approximate
true
artifact size bytes
27683881825
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
34B
parameter count
34000000000
parameter count is approximate
true
quantization level
Q8_0
context window
16000
context window is approximate
true
artifact size bytes
35856057185
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
69B
parameter count
69000000000
parameter count is approximate
true
quantization level
Q4_0
context window
2000
context window is approximate
true
artifact size bytes
38872431233
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
69B
parameter count
69000000000
parameter count is approximate
true
quantization level
Q4_0
context window
16000
context window is approximate
true
artifact size bytes
38872431040
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
69B
parameter count
69000000000
parameter count is approximate
true
quantization level
F16
context window
16000
context window is approximate
true
artifact size bytes
137957225856
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace