publisher · 70 variants · 74 roots
| root | family | variants | benchmarks |
|---|---|---|---|
| meta-llama/Llama-3.2-3B-Instruct | llama | 29 | 1 |
| meta-llama/Llama-3.1-8B-Instruct | llama | 22 | 1 |
| meta-llama/Meta-Llama-3-8B | llama | 22 | 10 |
| meta-llama/Llama-3.2-1B-Instruct | llama | 16 | 1 |
| meta-llama/Llama-3.3-70B-Instruct | llama | 16 | 1 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | llama | 13 | 0 |
| meta-llama/Meta-Llama-3-8B-Instruct | llama | 12 | 0 |
| meta-llama/Llama-3.1-8B | llama | 11 | 10 |
| meta-llama/Llama-3.2-3B | llama | 11 | 3 |
| meta-llama/Meta-Llama-3.1-8B | llama | 11 | 0 |
| meta-llama/Llama-3.2-1B | llama | 10 | 1 |
| meta-llama/Llama-2-7b-hf | llama | 9 | 6 |
| meta-llama/Meta-Llama-3.1-8B-Instruct | llama | 9 | 6 |
| meta-llama/Llama-3.1-70B | llama | 7 | 13 |
| meta-llama/Meta-Llama-3.1-70B-Instruct | llama | 7 | 0 |
| meta-llama/Llama-3.2-11B-Vision-Instruct | llama | 6 | 0 |
| meta-llama/Meta-Llama-3-70B-Instruct | llama | 6 | 2 |
| meta-llama/Llama-2-13b-hf | llama | 6 | 6 |
| meta-llama/Meta-Llama-3.1-70B | llama | 6 | 0 |
| meta-llama/Meta-Llama-3.1-405B | llama | 6 | 0 |
| meta-llama/Llama-3.1-70B-Instruct | llama | 5 | 2 |
| meta-llama/Llama-2-7b-chat-hf | llama | 5 | 4 |
| meta-llama/Llama-2-13b-chat-hf | llama | 5 | 4 |
| meta-llama/Meta-Llama-3-70B | llama | 5 | 8 |
| meta-llama/Llama-2-70b-hf | llama | 5 | 6 |
| meta-llama/Llama-3.2-90B-Vision-Instruct | llama | 4 | 0 |
| meta-llama/Llama-2-70b-chat-hf | llama | 4 | 4 |
| meta-llama/Llama-4-Maverick-17B-128E | llama | 4 | 0 |
| meta-llama/Llama-3.1-405B-Instruct | llama | 3 | 0 |
| meta-llama/Llama-Guard-3-1B | llama | 3 | 0 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct | llama | 3 | 0 |
| meta-llama/Llama-4-Scout-17B-16E | llama | 3 | 0 |
| meta-llama/Llama-3.2-11B-Vision | llama | 3 | 0 |
| meta-llama/Llama-Guard-4-12B | llama | 2 | 0 |
| meta-llama/Llama-3.1-405B | llama | 2 | 10 |
| meta-llama/CodeLlama-7b-hf | llama | 2 | 0 |
| meta-llama/Llama-2-7b | llama | 2 | 4 |
| meta-llama/Meta-Llama-3.1-405B-Instruct | llama | 2 | 0 |
| meta-llama/Llama-3-8B-Instruct | llama | 2 | 0 |
| meta-llama/Prompt-Guard-86M | llama | 1 | 1 |
| meta-llama/Llama-Prompt-Guard-2-86M | llama | 1 | 0 |
| meta-llama/Llama-Prompt-Guard-2-22M | llama | 1 | 0 |
| meta-llama/Meta-Llama-Guard-2-8B | llama | 1 | 0 |
| meta-llama/LlamaGuard-7b | llama | 1 | 0 |
| meta-llama/CodeLlama-7b-Instruct-hf | llama | 1 | 0 |
| meta-llama/Llama-Guard-3-11B-Vision | llama | 1 | 0 |
| meta-llama/CodeLlama-70b-Instruct-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-34b-Instruct-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-13b-Instruct-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-7b-Python-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-13b-hf | llama | 1 | 0 |
| meta-llama/Llama-3.2-90B-Vision | llama | 1 | 0 |
| meta-llama/Llama-2-7b-chat | llama | 1 | 4 |
| meta-llama/Llama-2-13b | llama | 1 | 4 |
| meta-llama/CodeLlama-34b-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-70b-Python-hf | llama | 1 | 0 |
| meta-llama/Llama-2-70b | llama | 1 | 4 |
| meta-llama/Llama-2-13b-chat | llama | 1 | 4 |
| meta-llama/Llama-4-Maverick-17B-128E-Original | llama | 1 | 0 |
| meta-llama/Llama-2-70b-chat | llama | 1 | 4 |
| meta-llama/CodeLlama-13b-Python-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-34b-Python-hf | llama | 1 | 0 |
| meta-llama/CodeLlama-70b-hf | llama | 1 | 0 |
| meta-llama/Llama-4-Scout-17B-16E-Original | llama | 1 | 0 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | llama | 1 | 0 |
| meta-llama/Llama-3-70B-Instruct | llama | 1 | 0 |
| meta-llama/Meta-Llama-3.1-681B-Instruct | llama | 1 | 0 |
| meta-llama/Llama-Guard-3-8B | llama | 0 | 0 |
| meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8 | llama | 0 | 0 |
| meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 | llama | 0 | 0 |
| meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 | llama | 0 | 0 |
| meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 | llama | 0 | 0 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct-Original | llama | 0 | 0 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original | llama | 0 | 0 |
| variant | kind | quant | vRAM | dl | root |
|---|---|---|---|---|---|
| Llama-3.2-1B-Instruct | original | bf16 | 2,529 | 10,196,211 | meta-llama/Llama-3.2-1B-Instruct |
| Llama-3.1-8B-Instruct | original | bf16 | 7,952,157 | meta-llama/Meta-Llama-3.1-8B | |
| Prompt-Guard-86M | original | bf16 | 4,480,135 | meta-llama/Prompt-Guard-86M | |
| Llama-3.2-1B | original | bf16 | 2,529 | 1,796,222 | meta-llama/Llama-3.2-1B |
| Llama-3.2-3B-Instruct | original | bf16 | 2,529 | 1,773,508 | meta-llama/Llama-3.2-3B-Instruct |
| Meta-Llama-3-8B-Instruct | original | bf16 | 1,692,222 | meta-llama/Meta-Llama-3-8B-Instruct | |
| Meta-Llama-3-8B | original | bf16 | 1,564,654 | meta-llama/Meta-Llama-3-8B | |
| Llama-3.1-8B | original | bf16 | 1,555,296 | meta-llama/Llama-3.1-8B | |
| Llama-3.1-70B-Instruct | original | bf16 | 1,268,205 | meta-llama/Meta-Llama-3.1-70B | |
| Llama-2-7b-hf | original | bf16 | 70 | 712,004 | meta-llama/Llama-2-7b-hf |
| Llama-3.3-70B-Instruct | original | bf16 | 635,792 | meta-llama/Llama-3.1-70B | |
| Llama-2-7b-chat-hf | original | bf16 | 70 | 563,871 | meta-llama/Llama-2-7b-chat-hf |
| Llama-3.2-3B | original | bf16 | 2,529 | 535,893 | meta-llama/Llama-3.2-3B |
| Llama-4-Scout-17B-16E-Instruct | original | bf16 | 447,101 | meta-llama/Llama-4-Scout-17B-16E | |
| Llama-3.1-405B-FP8 | fp8 | fp8 | 402,157 | meta-llama/Llama-3.1-405B-Instruct | |
| Llama-2-13b-chat-hf | original | bf16 | 212,789 | meta-llama/Llama-2-13b-chat-hf | |
| Llama-Guard-4-12B | original | bf16 | 188,993 | meta-llama/Llama-Guard-4-12B | |
| Meta-Llama-3-70B | original | bf16 | 142,671 | meta-llama/Meta-Llama-3-70B | |
| Llama-Guard-3-8B | original | bf16 | 127,894 | meta-llama/Meta-Llama-3.1-8B | |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | fp8 | fp8 | 123,211 | meta-llama/Llama-4-Maverick-17B-128E | |
| Llama-3.2-11B-Vision-Instruct | original | bf16 | 113,168 | meta-llama/Llama-3.2-11B-Vision-Instruct | |
| Llama-3.1-405B-Instruct | original | bf16 | 111,259 | meta-llama/Meta-Llama-3.1-405B | |
| Llama-3.1-405B | original | bf16 | 109,868 | meta-llama/Llama-3.1-405B | |
| Meta-Llama-3-70B-Instruct | original | bf16 | 108,127 | meta-llama/Meta-Llama-3-70B | |
| Llama-Prompt-Guard-2-86M | original | bf16 | 90,832 | meta-llama/Llama-Prompt-Guard-2-86M | |
| Llama-Guard-3-1B | original | bf16 | 59,518 | meta-llama/Llama-Guard-3-1B | |
| Llama-4-Maverick-17B-128E-Instruct | original | bf16 | 55,664 | meta-llama/Llama-4-Maverick-17B-128E | |
| Llama-3.2-90B-Vision-Instruct | original | bf16 | 49,468 | meta-llama/Llama-3.2-90B-Vision-Instruct | |
| Llama-3.1-70B | original | bf16 | 43,290 | meta-llama/Llama-3.1-70B | |
| Llama-4-Scout-17B-16E | original | bf16 | 32,494 | meta-llama/Llama-4-Scout-17B-16E | |
| Llama-2-13b-hf | original | bf16 | 23,717 | meta-llama/Llama-2-13b-hf | |
| Llama-Prompt-Guard-2-22M | original | bf16 | 16,729 | meta-llama/Llama-Prompt-Guard-2-22M | |
| Llama-3.1-405B-Instruct-FP8 | fp8 | fp8 | 15,725 | meta-llama/Meta-Llama-3.1-405B-Instruct | |
| Llama-Guard-3-8B-INT8 | bnb-4bit | 4bit | 12,509 | — | |
| Llama-2-70b-chat-hf | original | bf16 | 10,681 | meta-llama/Llama-2-70b-chat-hf | |
| Llama-3.2-11B-Vision | original | bf16 | 9,398 | meta-llama/Llama-3.2-11B-Vision | |
| Meta-Llama-Guard-2-8B | original | bf16 | 6,285 | meta-llama/Meta-Llama-Guard-2-8B | |
| Llama-2-70b-hf | original | bf16 | 6,129 | meta-llama/Llama-2-70b-hf | |
| LlamaGuard-7b | original | bf16 | 3,077 | meta-llama/LlamaGuard-7b | |
| CodeLlama-7b-Instruct-hf | original | bf16 | 2,745 | meta-llama/CodeLlama-7b-Instruct-hf | |
| Llama-Guard-3-11B-Vision | original | bf16 | 2,678 | meta-llama/Llama-Guard-3-11B-Vision | |
| CodeLlama-7b-hf | original | bf16 | 992 | meta-llama/CodeLlama-7b-hf | |
| Llama-4-Maverick-17B-128E | original | bf16 | 736 | meta-llama/Llama-4-Maverick-17B-128E | |
| CodeLlama-70b-Instruct-hf | original | bf16 | 617 | meta-llama/CodeLlama-70b-Instruct-hf | |
| CodeLlama-34b-Instruct-hf | original | bf16 | 540 | meta-llama/CodeLlama-34b-Instruct-hf | |
| CodeLlama-13b-Instruct-hf | original | bf16 | 535 | meta-llama/CodeLlama-13b-Instruct-hf | |
| Llama-2-7b | original | bf16 | 139 | meta-llama/Llama-2-7b | |
| CodeLlama-7b-Python-hf | original | bf16 | 117 | meta-llama/CodeLlama-7b-Python-hf | |
| CodeLlama-13b-hf | original | bf16 | 93 | meta-llama/CodeLlama-13b-hf | |
| Llama-3.2-90B-Vision | original | bf16 | 93 | meta-llama/Llama-3.2-90B-Vision | |
| Llama-3.2-3B-Instruct-QLORA_INT4_EO8 | original | bf16 | 78 | meta-llama/Llama-3.2-3B | |
| Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 | original | bf16 | 57 | meta-llama/Llama-3.2-1B | |
| Llama-2-7b-chat | original | bf16 | 53 | meta-llama/Llama-2-7b-chat | |
| Llama-2-13b | original | bf16 | 47 | meta-llama/Llama-2-13b | |
| Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 | original | bf16 | 39 | meta-llama/Llama-3.2-3B | |
| Llama-3.2-1B-Instruct-QLORA_INT4_EO8 | original | bf16 | 35 | meta-llama/Llama-3.2-1B | |
| CodeLlama-34b-hf | original | bf16 | 32 | meta-llama/CodeLlama-34b-hf | |
| CodeLlama-70b-Python-hf | original | bf16 | 24 | meta-llama/CodeLlama-70b-Python-hf | |
| Llama-Guard-3-1B-INT4 | int4 | int4 | 15 | meta-llama/Llama-Guard-3-1B | |
| Llama-2-70b | original | bf16 | 14 | meta-llama/Llama-2-70b | |
| Llama-2-13b-chat | original | bf16 | 9 | meta-llama/Llama-2-13b-chat | |
| Llama-4-Maverick-17B-128E-Original | original | bf16 | 8 | meta-llama/Llama-4-Maverick-17B-128E-Original | |
| Llama-4-Scout-17B-16E-Instruct-Original | original | bf16 | 6 | meta-llama/Llama-4-Scout-17B-16E | |
| Llama-2-70b-chat | original | bf16 | 5 | meta-llama/Llama-2-70b-chat | |
| Llama-4-Maverick-17B-128E-Instruct-FP8-Original | fp8 | fp8 | 5 | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | |
| CodeLlama-13b-Python-hf | original | bf16 | 4 | meta-llama/CodeLlama-13b-Python-hf | |
| CodeLlama-34b-Python-hf | original | bf16 | 4 | meta-llama/CodeLlama-34b-Python-hf | |
| Llama-4-Maverick-17B-128E-Instruct-Original | original | bf16 | 4 | meta-llama/Llama-4-Maverick-17B-128E | |
| CodeLlama-70b-hf | original | bf16 | 3 | meta-llama/CodeLlama-70b-hf | |
| Llama-4-Scout-17B-16E-Original | original | bf16 | 2 | meta-llama/Llama-4-Scout-17B-16E-Original |