FitMyGPU

Models

Browse the model registry

Start with the newest or most useful models, browse by company, or jump to the full index below.

Start here

Models to explore first

Companies

Browse by source

Index

All models

ModelCompanyAt a glance
GPT-OSS 20BOpenAI21B total • 3.6B active • 128,000 context • 8 KV headsGPT-OSS 120BOpenAI117B total • 5.1B active • 128,000 context • 8 KV headsLlama 3.1 8BMeta Llama8B dense • 131,072 context • 8 KV headsLlama 3.1 70BMeta Llama70.6B dense • 131,072 context • 8 KV headsQwen 2.5 0.5BQwen490M dense • 32,768 context • 2 KV headsQwen 2.5 1.5BQwen1.5B dense • 32,768 context • 2 KV headsQwen 2.5 3BQwen3.1B dense • 32,768 context • 2 KV headsQwen 2.5 7BQwen7.6B dense • 131,072 context • 4 KV headsQwen 2.5 14BQwen14.7B dense • 131,072 context • 8 KV headsQwen 2.5 32BQwen32.5B dense • 131,072 context • 8 KV headsQwen 2.5 72BQwen72.7B dense • 131,072 context • 8 KV headsQwen 3 0.6BQwen600M dense • 32,768 context • 8 KV headsQwen 3 1.7BQwen1.7B dense • 32,768 context • 8 KV headsQwen 3 4BQwen4B dense • 131,072 context • 8 KV headsQwen 3 8BQwen8.2B dense • 131,072 context • 8 KV headsQwen 3 14BQwen14.8B dense • 131,072 context • 8 KV headsQwen 3 32BQwen32.8B dense • 131,072 context • 8 KV headsQwen 3 30B A3BQwen30.5B total • 3.3B active • 131,072 context • 4 KV headsQwen 3 235B A22BQwen235B total • 22B active • 131,072 context • 4 KV headsQwen 3 4B Thinking 2507Qwen4B dense • 262,144 context • 8 KV headsQwen 3 30B A3B Instruct 2507Qwen30.5B total • 3.3B active • 262,144 context • 4 KV headsQwen 3.5 0.8BQwen900M dense • 262,144 context • 2 KV headsQwen 3.5 2BQwen2B dense • 262,144 context • 2 KV headsQwen 3.5 4BQwen5B dense • 262,144 context • 4 KV headsQwen 3.5 9BQwen10B dense • 262,144 context • 4 KV headsQwen 3.5 27BQwen27B dense • 262,144 context • 4 KV headsQwen 3.5 35B A3BQwen35B total • 3B active • 262,144 context • 2 KV headsQwen 3.5 122B A10BQwen122B total • 10B active • 262,144 context • 2 KV headsQwen 3.5 397B A17BQwen397B total • 17B active • 262,144 context • 2 KV headsQwen 3.6 27BQwen27B dense • 262,144 context • 4 KV headsQwen 3.6 35B A3BQwen35B total • 3B active • 262,144 context • 2 KV headsDeepSeek R1 Distill Qwen 1.5BDeepSeek1.5B dense • 131,072 context • 2 KV headsDeepSeek R1 Distill Qwen 7BDeepSeek7B dense • 131,072 context • 4 KV headsDeepSeek R1 Distill Qwen 14BDeepSeek14B dense • 131,072 context • 8 KV headsDeepSeek R1 Distill Qwen 32BDeepSeek32B dense • 131,072 context • 8 KV headsDeepSeek R1 Distill Llama 8BDeepSeek8B dense • 131,072 context • 8 KV headsDeepSeek R1 Distill Llama 70BDeepSeek70B dense • 131,072 context • 8 KV headsOpenReasoning Nemotron 1.5BNVIDIA1.5B dense • 32,768 context • 2 KV headsOpenReasoning Nemotron 7BNVIDIA7.6B dense • 131,072 context • 4 KV headsOpenReasoning Nemotron 14BNVIDIA14.7B dense • 131,072 context • 8 KV headsOpenReasoning Nemotron 32BNVIDIA32.5B dense • 131,072 context • 8 KV headsGemma 2 9BGemma9.2B dense • 8,192 context • 8 KV headsGemma 2 27BGemma27B dense • 8,192 context • 16 KV headsMistral Nemo 12BMistral12.2B dense • 128,000 context • 8 KV headsMixtral 8x7BMistral46.7B total • 12.9B active • 32,768 context • 8 KV headsPhi-4 14BMicrosoft Phi14.7B dense • 16,384 context • 10 KV heads