built by recursal.ai

Models

llama31-8b-16k
meta-llama/Meta-Llama-3.1-8B-Instruct
Warm
3,466
5,607,354
mistral-v02-7b-std-lc
mistralai/Mistral-7B-Instruct-v0.2
Loading
2,614
3,618,808
mistral-nemo-12b-lc
mistralai/Mistral-Nemo-Instruct-2407
Warm
1,381
2,483,361
llama3-8b-8k
meta-llama/Meta-Llama-3-8B-Instruct
Warm
3,766
1,614,707
llama31-8b-16k
meta-llama/Meta-Llama-3.1-8B
Warm
1,283
728,127
llama3-8b-8k
meta-llama/Meta-Llama-3-8B
Loading
5,971
499,938
llama33-70b-16k
meta-llama/Llama-3.3-70B-Instruct
Warm
1,667
466,329
llama31-70b-16k
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Warm
1,997
381,422
llama31-70b-16k
meta-llama/Meta-Llama-3.1-70B-Instruct
Warm
774
340,006
llama33-70b-16k
unsloth/Llama-3.3-70B-Instruct
Warm
34
286,653
llama31-70b-16k
mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16
Loading
1
255,479
llama31-8b-16k
mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
Warm
145
247,621
llama31-70b-16k
mlx-community/Meta-Llama-3.1-70B-Instruct-bf16-CORRECTED
Cold
0
241,215
llama31-70b-16k
NousResearch/Meta-Llama-3.1-70B-Instruct
Warm
9
233,200
mistral-v02-7b-std-lc
HuggingFaceH4/zephyr-7b-beta
Loading
1,643
229,797
llama31-8b-16k
VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
Warm
32
222,992
qwen2-32b-lc
Qwen/Qwen2.5-Coder-32B-Instruct
Warm
1,488
216,609
llama2-13b-4k
meta-llama/Llama-2-13b-chat-hf
Warm
1,044
201,664
llama3-8b-8k
DeepMount00/Llama-3-8b-Ita
Loading
24
187,717
llama31-8b-16k
meta-llama/Llama-Guard-3-8B
Warm
149
183,209