🌐 All Models
1,750 models · Page 28 of 49
Nvidia Nemotron 3 Super 120B A12b Fp8
Nvidia Nemotron Nano 9B V2
Gemma 3 27B Pt
nim/mistralai/mixtral-8x7b-instruct-v01
Qwen3 Next 80B A3b Instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Llama 4 Maverick Instruct (17Bx128E) FP8
Glm 4.5 Air Fp8
Llama 4 Maverick 17B 128E
Qwen3 4B Base
Qwen2.5 7B
Qwen2.5-VL (72B) Instruct
Qwen3 Next 80B A3b Instruct Fp8
Qwen3 0.6B Base
Qwen3 30B A3b
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Mistral (7B) Instruct v0.3
Mixtral 8X7b V0.1
nim/meta/llama-3.2-11b-vision-instruct
Qwen 2 (7B)
Qwen3 235B A22B FP8
Qwen 2 Instruct (1.5B)
Qwen QwQ-32B
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...
Qwen2.5 7B Instruct
Meta Llama 3.1 405B Instruct
Gemma-2 Instruct (27B)
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
nim/meta/llama-3.3-70b-instruct
Minimax M1 80K
Llama 3.2 1B
Deepseek V3.2 Exp
Qwen3 Next 80B A3b Thinking
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...