Open R1: How to use OlympicCoder locally for coding?
•
62
LM Studio
company
Verified
AI & ML interests
Discover, download, and experiment with local/open LLMs.
Articles
Fast, small, and capable coding model you can run locally on your computer! Requires 8GB+ of RAM.
-
Code Llama: Open Foundation Models for Code
Paper • 2308.12950 • Published • 27 -
TheBloke/CodeLlama-7B-Instruct-GGUF
Text Generation • 7B • Updated • 15.5k • 136 -
TheBloke/CodeLlama-34B-Instruct-GGUF
Text Generation • 34B • Updated • 3.47k • 102 -
codellama/CodeLlama-7b-Instruct-hf
Text Generation • 7B • Updated • 198k • 241
GGUF quants for the new Qwen1.5 model (https://qwenlm.github.io/blog/qwen1.5/)
Models trained and/or fine-tuned for coding tasks
-
lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF
Text Generation • 16B • Updated • 5.86k • 54 -
lmstudio-community/Codestral-22B-v0.1-GGUF
Text Generation • 22B • Updated • 8.99k • 26 -
lmstudio-community/codegemma-1.1-7b-it-GGUF
Text Generation • 9B • Updated • 582 • 5 -
lmstudio-community/starcoder2-15b-instruct-v0.1-GGUF
Text Generation • 16B • Updated • 468 • 3
Models trained to perform well in more than one language
How to use: Download a "mmproj" model file + one or more of the primary model files.
General purpose chatbot-like LLMs you can run on your computer
-
lmstudio-community/Meta-Llama-3-8B-Instruct-BPE-fix-GGUF
Text Generation • 8B • Updated • 120 • 11 -
lmstudio-community/gemma-2-9b-it-GGUF
Text Generation • 9B • Updated • 4.3k • 27 -
lmstudio-community/Phi-3.1-mini-4k-instruct-GGUF
Text Generation • 4B • Updated • 1.02k • 23 -
bartowski/dolphin-2.9.3-mistral-7B-32k-GGUF
Text Generation • 7B • Updated • 229 • 8
Models specifically fine-tuned for function calling, tool-use, or RAG
Very small Large Language Models. Runs fast, might be quirky
Fast, small, and capable coding model you can run locally on your computer! Requires 8GB+ of RAM.
-
Code Llama: Open Foundation Models for Code
Paper • 2308.12950 • Published • 27 -
TheBloke/CodeLlama-7B-Instruct-GGUF
Text Generation • 7B • Updated • 15.5k • 136 -
TheBloke/CodeLlama-34B-Instruct-GGUF
Text Generation • 34B • Updated • 3.47k • 102 -
codellama/CodeLlama-7b-Instruct-hf
Text Generation • 7B • Updated • 198k • 241
How to use: Download a "mmproj" model file + one or more of the primary model files.
GGUF quants for the new Qwen1.5 model (https://qwenlm.github.io/blog/qwen1.5/)
General purpose chatbot-like LLMs you can run on your computer
-
lmstudio-community/Meta-Llama-3-8B-Instruct-BPE-fix-GGUF
Text Generation • 8B • Updated • 120 • 11 -
lmstudio-community/gemma-2-9b-it-GGUF
Text Generation • 9B • Updated • 4.3k • 27 -
lmstudio-community/Phi-3.1-mini-4k-instruct-GGUF
Text Generation • 4B • Updated • 1.02k • 23 -
bartowski/dolphin-2.9.3-mistral-7B-32k-GGUF
Text Generation • 7B • Updated • 229 • 8
Models trained and/or fine-tuned for coding tasks
-
lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF
Text Generation • 16B • Updated • 5.86k • 54 -
lmstudio-community/Codestral-22B-v0.1-GGUF
Text Generation • 22B • Updated • 8.99k • 26 -
lmstudio-community/codegemma-1.1-7b-it-GGUF
Text Generation • 9B • Updated • 582 • 5 -
lmstudio-community/starcoder2-15b-instruct-v0.1-GGUF
Text Generation • 16B • Updated • 468 • 3
Models specifically fine-tuned for function calling, tool-use, or RAG
Models trained to perform well in more than one language
Very small Large Language Models. Runs fast, might be quirky