Ollama · phind-codellama

<img src="https://user-images.githubusercontent.com/633681/264120182-4a05afc9-0003-410e-8ac5-a7745dedaba8.png" style="max-width:60%" /> Phind CodeLlama is a code generation model based on CodeLlama 3…

ollama/phind-codellama

<img src="https://user-images.githubusercontent.com/633681/264120182-4a05afc9-0003-410e-8ac5-a7745dedaba8.png" style="max-width:60%" />

Phind CodeLlama is a code generation model based on CodeLlama 34B fine-tuned for instruct use cases. There are two versions of the model: `v1` and `v2`. `v1` is based on CodeLlama 34B and CodeLlama-Python 34B. `v2` is an iteration on `v1`, trained on an additional 1.5B tokens of high-quality programming-related data.

## Usage

### CLI

Open the terminal and run `ollama run phind-codellama`

### API

Example

```bash curl -X POST http://localhost:11434/api/generate -d '{ "model": "phind-codellama", "prompt":"Implement a linked list in C++" }' ```

## Memory requirements

- 34b models generally require at least 32GB of RAM

## References

[Beating GPT-4 on HumanEval with a Fine-Tuned CodeLlama-34B](https://www.phind.com/blog/code-llama-beats-gpt4 )

[HuggingFace](https://huggingface.co/Phind)

Specifications & capabilities

Published model ID
phind-codellama

Deployments & artifacts

41–49 / 49

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
20219907306
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
19146427626
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
23237184746
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
25329749226
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
23838805226
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
23237184746
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
27683884266
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
35856059626
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
19052055786
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