Explore Models

Flux.1 [dev]

Flux.1 [dev]

IMAGE
New

A new SOTA image generation model that is outstanding in prompt following and visual quality.

Llama-3.1-405B-BASE

Llama-3.1-405B-BASE

LLM
BF16
Popular

Still the SOTA base completion model but better because it's BF16.

DeepSeek-R1

DeepSeek-R1

LLM
FP8
New

The best open-source reasoner LLM released by DeepSeek.

All Models

Text Models

QwQ-32B

QwQ-32B

The lastest Qwen reasoning model.

LLM
BF16
New
DeepSeek-R1

DeepSeek-R1

The best open-source reasoner LLM released by DeepSeek.

LLM
FP8
New
DeepSeek-V3

DeepSeek-V3

The best open-source LLM released by DeepSeek.

LLM
FP8
New
Llama-3.3-70B

Llama-3.3-70B

Meta's latest 70B LLM with performance comparable to llama 3.1 405B

LLM
FP8
Popular
QwQ-32B-Preview

QwQ-32B-Preview

The lastest reasoner from the Qwen Team.

LLM
FP8
Qwen2.5-Coder-32B

Qwen2.5-Coder-32B

The best coder from the Qwen Team.

LLM
FP8
Llama-3.2-3B

Llama-3.2-3B

The latest Llama 3.2 instruction-tuned model by Meta.

LLM
FP8
Qwen2.5-72B

Qwen2.5-72B

The latest Qwen LLM with more knowledge in coding and math.

LLM
BF16
Llama-3-70B

Llama-3-70B

A highly efficient and powerful model designed for a variety of tasks.

LLM
FP8
Hermes-3-70B

Hermes-3-70B

The latest flagship model in the Hermes series and the first full parameter fine-tune since the release of Llama 3.1.

LLM
FP8
Llama-3.1-405B

Llama-3.1-405B

The Biggest and Best open-source AI model trained by Meta, beating GPT-4o across most benchmarks.

LLM
BF16
Llama-3.1-8B

Llama-3.1-8B

The smallest and fastest member of the Llama 3.1 family.

LLM
FP8
Llama-3.1-70B

Llama-3.1-70B

The best LLM at its size with faster response times compared to the 405B model.

LLM
FP8