coder · Ollama

[

qwen3-coder

Alibaba's performant long context models for agentic and coding tasks.

toolscloud30b480b

5.1M Pulls10 TagsUpdated 7 months ago

](https://ollama.com/library/qwen3-coder)

[

qwen2.5-coder

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

tools0.5b1.5b3b7b14b32b

15M Pulls199 TagsUpdated 11 months ago

](https://ollama.com/library/qwen2.5-coder)

[

deepseek-coder

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

1.3b6.7b33b

4.1M Pulls102 TagsUpdated 2 years ago

](https://ollama.com/library/deepseek-coder)

[

deepseek-coder-v2

An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

16b236b

2.5M Pulls64 TagsUpdated 1 year ago

](https://ollama.com/library/deepseek-coder-v2)

[

starcoder2

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

3b7b15b

2.8M Pulls67 TagsUpdated 1 year ago

](https://ollama.com/library/starcoder2)

[

deepcoder

DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

1.5b14b

860.3K Pulls9 TagsUpdated 1 year ago

](https://ollama.com/library/deepcoder)

[

yi-coder

Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

1.5b9b

959.9K Pulls67 TagsUpdated 1 year ago

](https://ollama.com/library/yi-coder)

[

opencoder

OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.

1.5b8b

587.6K Pulls9 TagsUpdated 1 year ago

](https://ollama.com/library/opencoder)

[

dolphincoder

A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.

7b15b

931.1K Pulls35 TagsUpdated 2 years ago

](https://ollama.com/library/dolphincoder)

[

starcoder

StarCoder is a code generation model trained on 80+ programming languages.

1b3b7b15b

1.1M Pulls100 TagsUpdated 2 years ago

](https://ollama.com/library/starcoder)

[

sqlcoder

SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks

7b15b

970.1K Pulls48 TagsUpdated 2 years ago

](https://ollama.com/library/sqlcoder)

[

deepseek-v2.5

An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

236b

271.4K Pulls7 TagsUpdated 1 year ago

](https://ollama.com/library/deepseek-v2.5)

[

command-a

111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI

tools111b

212.9K Pulls5 TagsUpdated 1 year ago

](https://ollama.com/library/command-a)

[

cogito-2.1

The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.

cloud671b

177.9K Pulls6 TagsUpdated 5 months ago

](https://ollama.com/library/cogito-2.1)

[

codellama

A large language model that can use text prompts to generate and discuss code.

7b13b34b70b

5.5M Pulls199 TagsUpdated 1 year ago

](https://ollama.com/library/codellama)

[

codegemma

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.

2b7b

3M Pulls85 TagsUpdated 1 year ago

](https://ollama.com/library/codegemma)

[

mistral-large

Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.

tools123b

1.2M Pulls32 TagsUpdated 1 year ago

](https://ollama.com/library/mistral-large)

[

dolphin-mixtral

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

8x7b8x22b

1.7M Pulls70 TagsUpdated 1 year ago

](https://ollama.com/library/dolphin-mixtral)

[

codestral

Codestral is Mistral AI’s first-ever code model designed for code generation tasks.

22b

1.2M Pulls17 TagsUpdated 1 year ago

](https://ollama.com/library/codestral)

[

codeqwen

CodeQwen1.5 is a large language model pretrained on a large amount of code data.

7b

1M Pulls30 TagsUpdated 1 year ago

](https://ollama.com/library/codeqwen)

[

codegeex4

A versatile model for AI software development scenarios, including code completion.

9b

649.4K Pulls17 TagsUpdated 1 year ago

](https://ollama.com/library/codegeex4)

[

tulu3

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.

8b70b

358.9K Pulls9 TagsUpdated 1 year ago

](https://ollama.com/library/tulu3)

[

codeup

Great code generation model based on Llama2.

13b

555.5K Pulls19 TagsUpdated 2 years ago

](https://ollama.com/library/codeup)

[

codebooga

A high-performing code instruct model created by merging two existing code models.

34b

466.6K Pulls16 TagsUpdated 2 years ago

](https://ollama.com/library/codebooga)

[

cogito

Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.

tools3b8b14b32b70b

2M Pulls20 TagsUpdated 1 year ago

](https://ollama.com/library/cogito)

[

command-r-plus

Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

tools104b

752.8K Pulls21 TagsUpdated 1 year ago

](https://ollama.com/library/command-r-plus)

[

command-r7b

The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

tools7b

253.7K Pulls5 TagsUpdated 1 year ago

](https://ollama.com/library/command-r7b)

[

qwen3.6

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

visiontoolsthinking27b35b

772.3K Pulls22 TagsUpdated 1 week ago

](https://ollama.com/library/qwen3.6)

[

devstral-small-2

24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

visiontoolscloud24b

811.9K Pulls6 TagsUpdated 4 months ago

](https://ollama.com/library/devstral-small-2)

[

glm-ocr

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

visiontools

407.4K Pulls3 TagsUpdated 2 months ago

](https://ollama.com/library/glm-ocr)

[

rnj-1

Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

toolscloud8b

453.4K Pulls6 TagsUpdated 4 months ago

](https://ollama.com/library/rnj-1)

[

devstral-2

123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

toolscloud123b

208.1K Pulls6 TagsUpdated 4 months ago

](https://ollama.com/library/devstral-2)

[

minimax-m2.1

Exceptional multilingual capabilities to elevate code engineering

toolscloud

44K Pulls1 TagUpdated 4 months ago

](https://ollama.com/library/minimax-m2.1)

[

llava

🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.

vision7b13b34b

14M Pulls98 TagsUpdated 2 years ago

](https://ollama.com/library/llava)

[

granite3.2-vision

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

visiontools2b

901.8K Pulls5 TagsUpdated 1 year ago

](https://ollama.com/library/granite3.2-vision)

[

dolphin-mistral

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

7b

1.4M Pulls120 TagsUpdated 2 years ago

](https://ollama.com/library/dolphin-mistral)

[

athene-v2

Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

tools72b

555.8K Pulls17 TagsUpdated 1 year ago

](https://ollama.com/library/athene-v2)

[

stable-code

Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.

3b

985.1K Pulls36 TagsUpdated 2 years ago

](https://ollama.com/library/stable-code)

[

wizardcoder

State-of-the-art code generation model

33b

965.7K Pulls67 TagsUpdated 2 years ago

](https://ollama.com/library/wizardcoder)

[

phind-codellama

Code generation model based on Code Llama.

34b

900.5K Pulls49 TagsUpdated 2 years ago

](https://ollama.com/library/phind-codellama)

[

falcon2

Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.

11b

503.9K Pulls17 TagsUpdated 1 year ago

](https://ollama.com/library/falcon2)

[

open-orca-platypus2

Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

13b

478.7K Pulls17 TagsUpdated 2 years ago

](https://ollama.com/library/open-orca-platypus2)

[

nemotron-cascade-2

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

toolsthinking30b

109.5K Pulls3 TagsUpdated 1 month ago

](https://ollama.com/library/nemotron-cascade-2)

[

coder11v/mycode1

a simple coding agent that can run commands.

visiontoolsthinkingaudio

16 Pulls1 TagUpdated 4 days ago

](https://ollama.com/coder11v/mycode1)

[

gemma3

The current, most capable model that runs on a single GPU.

visioncloud270m1b4b12b27b

36.3M Pulls29 TagsUpdated 4 months ago

](https://ollama.com/library/gemma3)

[

qwen3

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

toolsthinking0.6b1.7b4b8b14b30b32b235b

28.2M Pulls58 TagsUpdated 6 months ago

](https://ollama.com/library/qwen3)

[

llama2

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

7b13b70b

6.8M Pulls102 TagsUpdated 2 years ago

](https://ollama.com/library/llama2)

[

granite3.3

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

tools2b8b

1M Pulls3 TagsUpdated 1 year ago

](https://ollama.com/library/granite3.3)

[

exaone-deep

EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.

2.4b7.8b32b

731.7K Pulls13 TagsUpdated 1 year ago

](https://ollama.com/library/exaone-deep)

[

aya-expanse

Cohere For AI's language models trained to perform well across 23 different languages.

tools8b32b

906.5K Pulls33 TagsUpdated 1 year ago

](https://ollama.com/library/aya-expanse)

[

llama3-chatqa

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

8b70b

947.1K Pulls35 TagsUpdated 1 year ago

](https://ollama.com/library/llama3-chatqa)

[

nemotron-mini

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

tools4b

632.8K Pulls17 TagsUpdated 1 year ago

](https://ollama.com/library/nemotron-mini)

[

exaone3.5

EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

2.4b7.8b32b

494.4K Pulls13 TagsUpdated 1 year ago

](https://ollama.com/library/exaone3.5)

[

solar

A compact, yet powerful 10.7B large language model designed for single-turn conversation.

10.7b

902.4K Pulls32 TagsUpdated 2 years ago

](https://ollama.com/library/solar)

[

stablelm-zephyr

A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.

3b

500.5K Pulls17 TagsUpdated 2 years ago

](https://ollama.com/library/stablelm-zephyr)

[

alfred

A robust conversational model designed to be used for both chat and instruct use cases.

40b

225.1K Pulls7 TagsUpdated 2 years ago

](https://ollama.com/library/alfred)

[

codermillat/mistral-7b-indian-university-guidance

Fine-tuned Mistral 7B for Bangladeshi students seeking Indian university guidance—covering admissions, scholarships, visas, and degree equivalence.

1 Pull1 TagUpdated 2 weeks ago

](https://ollama.com/codermillat/mistral-7b-indian-university-guidance)

[

coderindajungle/medllama3

72 Pulls1 TagUpdated 1 year ago

](https://ollama.com/coderindajungle/medllama3)

[

coderindajungle/llama-3b-8b

the first model retrained by Toni

11 Pulls1 TagUpdated 1 year ago

](https://ollama.com/coderindajungle/llama-3b-8b)