Best coding LLMs to run locally | Can I Run This LLM?

33 models in this collection.

GLM 5

GLM · 744B

chatcodingreasoningtool-use+2

DeepSeek V3.2

DeepSeek · 685B

chatcodingreasoningtool-use+2

GLM 4.7

GLM · 355B

chatcodingreasoningtool-use+2

MiMo V2 Flash

MiMo · 309B

chatcodingreasoningtool-use+2

MiniMax M2.5

MiniMax · 230B

chatcodingreasoningtool-use+2

Step 3.5 Flash

Step · 196B

chatcodingreasoningtool-use+2

Devstral 2 123B

Mistral · 123B

codingtool-usereasoningfrontier

GPT-OSS 120B

GPT-OSS · 120B

chatcodingreasoningtool-use+2

Qwen3 Coder Next 80B A3B

Qwen · 80B

codingtool-usereasoningmoe+2

Llama 3.1 70B

Llama · 70B

chatgeneralcoding

Llama 3.3 70B

Llama · 70B

Best for High-end workstations

chatgeneralcodinginstruct

Qwen3.6 35B A3B

Qwen · 35B

chatcodingreasoningtool-use+2

CodeLlama 34B

CodeLlama · 34B

codinginstructchat

Qwen 2.5 Coder 32B

Qwen · 32B

codinginstructchat

Qwen3 Coder 30B A3B

Qwen · 30B

codingtool-usereasoningmoe+1

Devstral Small 2 24B

Mistral · 24B

codingtool-usereasoning

Codestral 22B

Mistral · 22B

Best for Advanced coding assistants

GPT-OSS 20B

GPT-OSS · 20B

chatcodingreasoningtool-use+1

DeepSeek Coder V2 Lite 16B

DeepSeek · 16B

StarCoder2 15B

StarCoder · 15B

Phi-3 Medium 14B

Phi · 14B

chatgeneralcoding

Phi-4 14B

Phi · 14B

Best for Analysis-heavy assistants

chatgeneralreasoningcoding

Phi-4 Reasoning 14B

Phi · 14B

chatreasoningcoding

Phi-4 Reasoning Plus 14B

Phi · 14B

chatreasoningcodingfrontier

CodeLlama 13B

CodeLlama · 13B

codinginstructchat

Llama 3.1 8B

Llama · 8B

Best for General use

chatgeneralcoding

CodeLlama 7B

CodeLlama · 7B

codinginstructchat

Qwen 2.5 Coder 7B

Qwen · 7B

Best for Code generation

codinginstructchat

StarCoder2 7B

StarCoder · 7B

Phi-3 Mini 3.8B

Phi · 3.8B

chatsmallcoding

Phi-4 Mini 3.8B

Phi · 3.8B

Best for Low-VRAM devices

chatsmallreasoningcoding

Stable Code 3B

StableCode · 3B

codingsmallchat

StarCoder2 3B

StarCoder · 3B

codingsmallfimchat