Warm

{ "id": "tinyllama-1b1", "created_at": "2025-06-12T09:08:30.540Z", "updated_at": "2026-03-10T07:33:26.434Z", "concurrency_cost": 1, "size": 1.1, "parameter_size": 1100000000, "context_length": 2048, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

TinyLlama/TinyLlama-1.1B-Chat-v1.0

1,835

1,361,375

T
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

codellama/CodeLlama-7b-hf

379

401,026

C
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

huggyllama/llama-7b

360

277,880

H
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

NousResearch/Llama-2-7b-hf

178

194,533

N
Warm

{ "id": "tinyllama-1b1", "created_at": "2025-06-12T09:08:30.540Z", "updated_at": "2026-03-10T07:33:26.434Z", "concurrency_cost": 1, "size": 1.1, "parameter_size": 1100000000, "context_length": 2048, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

LSX-UniWue/LLaMmlein_1B_prerelease

14

182,403

L
Warm

{ "id": "llama2-13b", "created_at": "2024-08-01T18:28:25.250Z", "updated_at": "2026-01-27T08:14:54.341Z", "concurrency_cost": 1, "size": 13, "parameter_size": 13000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

meta-llama/Llama-2-13b-chat-hf

1,128

167,620

M
Warm

{ "id": "llama2-13b", "created_at": "2024-08-01T18:28:25.250Z", "updated_at": "2026-01-27T08:14:54.341Z", "concurrency_cost": 1, "size": 13, "parameter_size": 13000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

cais/HarmBench-Llama-2-13b-cls

32

95,607

C
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

openlm-research/open_llama_7b

139

75,823

O
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

lmsys/vicuna-7b-v1.5

406

72,211

L
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

codellama/CodeLlama-7b-Instruct-hf

259

35,822

C
Warm

{ "id": "llama2-solar-10b7", "created_at": "2024-06-21T16:42:57.276Z", "updated_at": "2026-03-09T13:47:34.342Z", "concurrency_cost": 1, "size": 10.7, "parameter_size": 10700000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

upstage/SOLAR-10.7B-Instruct-v1.0

659

35,484

U
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

unsloth/llama-2-7b-chat

6

31,200

U
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

unsloth/llama-2-7b

20

27,449

U
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

NousResearch/Llama-2-7b-chat-hf

201

18,971

N
Warm

{ "id": "llama2-13b", "created_at": "2024-08-01T18:28:25.250Z", "updated_at": "2026-01-27T08:14:54.341Z", "concurrency_cost": 1, "size": 13, "parameter_size": 13000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

lmsys/vicuna-13b-v1.5

242

13,204

L
Warm

{ "id": "llama2-solar-10b7", "created_at": "2024-06-21T16:42:57.276Z", "updated_at": "2026-03-09T13:47:34.342Z", "concurrency_cost": 1, "size": 10.7, "parameter_size": 10700000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

upstage/SOLAR-10.7B-v1.0

324

12,987

U
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

defog/sqlcoder-7b-2

446

11,263

D
Warm

{ "id": "llama2-7b", "created_at": "2025-04-02T20:53:00.000Z", "updated_at": "2026-03-09T13:41:30.003Z", "concurrency_cost": 1, "size": 7, "parameter_size": 7000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

StanfordAIMI/GREEN-RadLlama2-7b

7

10,901

S
Warm

{ "id": "llama2-solar-10b7", "created_at": "2024-06-21T16:42:57.276Z", "updated_at": "2026-03-09T13:47:34.342Z", "concurrency_cost": 1, "size": 10.7, "parameter_size": 10700000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

NousResearch/Nous-Hermes-2-SOLAR-10.7B

209

10,222

N
Warm

{ "id": "llama2-70b", "created_at": "2026-05-07T20:02:40.158Z", "updated_at": "2026-05-07T20:02:40.158Z", "concurrency_cost": 4, "size": 69, "parameter_size": 69000000000, "context_length": 4096, "is_moe": false, "active_parameters": null, "vision_supported": false, "input_modalities": [ "text" ], "output_modalities": [ "text" ], "family": "llama2", "family_name": "Llama 2" }

sophosympatheia/Midnight-Miqu-70B-v1.5

268

8,941

S