🌙
Light Mode
Llama 3.3 70B Fast (Latest & Most Capable)
Llama 3.1 70B (High Performance)
Mistral Small 3.1 24B (Vision + Text)
QwQ 32B (Advanced Reasoning)
DeepSeek R1 Distill 32B (Reasoning)
Llama 3.1 8B (Recommended)
Llama 3.1 8B Fast (JSON Mode)
Llama 3.1 8B FP8 (Optimized)
Llama 3 8B (Fast)
Llama 3.2 3B (Lightweight)
Llama 3.2 11B Vision (Multimodal)
Gemma 3 12B (Multimodal)
Gemma 7B IT (Beta)
Mistral 7B Instruct
Hermes 2 Pro Mistral 7B (Function Calling)
Llama 2 7B Chat
Meta Llama 3 8B
Llama 3.1 8B AWQ
Llama 3 8B AWQ
Llama 2 13B Chat AWQ
Mistral 7B AWQ
OpenHermes 2.5 Mistral 7B
Starling LM 7B Beta (RLAIF)
UNA Cybertron 7B v2 (Beta)
Microsoft Phi-2 (Beta)
Qwen 1.5 1.8B Chat (Beta)
Mistral 7B v0.2 LoRA (Beta)
DeepSeek Math 7B (Beta)
DeepSeek Coder 6.7B AWQ (Beta)
DeepSeek Coder 6.7B Base AWQ (Beta)
Llama Guard 7B AWQ (Safety)
Neural Chat 7B v3.1
Zephyr 7B Beta
Qwen 1.5 0.5B Chat (Ultra Fast)
Qwen 1.5 7B Chat AWQ
Qwen 1.5 14B Chat AWQ
Send
