Llama 3.2 3b Model Hosting

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

meta-llama/Llama-3.2-3B-Instruct

2,095

4,929,515

M

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

meta-llama/Llama-3.2-3B

748

1,052,275

M

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

unsloth/Llama-3.2-3B-Instruct

87

214,741

U

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

unsloth/Llama-3.2-3B

18

36,318

U

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

NousResearch/Hermes-3-Llama-3.2-3B

175

13,871

N

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

radheneev/NetrAI-L3

1

8,892

R

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

baseten/Llama-3.2-3B-Instruct-pythonic

0

5,691

B

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

open-unlearning/tofu_Llama-3.2-3B-Instruct_full

1

5,028

O

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

prithivMLmods/DeepHermes-3-Llama-3-3B-Preview-abliterated

5

4,114

P

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

OctoThinker/OctoThinker-3B-Hybrid-Base

1

3,930

O

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

prithivMLmods/Llama-Doctor-3.2-3B-Instruct

7

3,423

P

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

alpindale/Llama-3.2-3B-Instruct

10

2,880

A

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

huihui-ai/Llama-3.2-3B-Instruct-abliterated

90

2,733

H

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

psychopenguin/indian_legal_llama3.2-3b-instruct

0

2,722

P

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

Bllossom/llama-3.2-Korean-Bllossom-3B

191

2,436

B

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

rinnic/llama3_2_3B-practice-area-ft-125k-1epochs

0

2,311

R

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

inference-net/Schematron-3B

331

2,291

I

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

LTS-VVE/Teuta

3

2,158

L

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

PASI1028/Llama-3.2-3B-Instruct

0

2,144

P

Warm

{ "id": "llama32-3b", "created_at": "2025-06-12T19:26:12.601Z", "updated_at": "2026-03-10T07:21:03.452Z", "concurrency_cost": 1, "size": 3.2, "family": "llama32", "context_length": 32768, "crawl": true, "vision_supported": false, "reference_model_id": "unsloth/Llama-3.2-3B", "backend": { "id": "router-s3", "created_at": "2026-01-27T07:15:05.230Z", "updated_at": "2026-01-27T07:15:05.230Z", "apiBaseURL": "https://router-s3.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.2" }

ParetoQaft/3B-base

0

2,133

P