LLM Models · meta-llama

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

✨ All 1877 Qwen 104 openai 91 OpenGVLab 70 internlm 63 deepseek-ai 62 meta-llama 62 tokyotech-llm 61 google 59 nvidia 58 tiiuae 54 allenai 53 zai-org 52

Llama-4-Maverick-17B-128E-Instruct-FP8

meta-llama

multimodal 400.0B ★ 14.0 ↓ 75.2K

Llama-4-Maverick-17B-128E-Instruct

meta-llama

multimodal 400.0B ★ 14.0 ↓ 11.8K

Llama-4-Maverick-17B-128E

meta-llama

open-source 17.0B ★ 14.0 ↓ 374

Meta: Llama 4 Maverick

meta-llama

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

closed-source ★ 14.0

Llama-4-Scout-17B-16E-Instruct

meta-llama

multimodal 109.0B ★ 10.0 ↓ 231.4K

Llama-4-Scout-17B-16E

meta-llama

multimodal 109.0B ★ 10.0 ↓ 10.6K

Meta: Llama 4 Scout

meta-llama

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

closed-source ★ 10.0

Llama-3.3-70B-Instruct

meta-llama

open-source 70.0B ★ 9.0 ↓ 549.3K

Llama-3.1-405B-FP8

meta-llama

open-source 405.0B ★ 8.0 ↓ 488.3K

Llama-3.1-405B

meta-llama

open-source 405.0B ★ 8.0 ↓ 141.7K

Llama-3.1-405B-Instruct

meta-llama