LiquidAI: LFM2-24B-A2B

Description

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.

Raw fields snapshot

{
  "id": "liquid/lfm-2-24b-a2b",
  "name": "LiquidAI: LFM2-24B-A2B",
  "description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.",
  "created": 1772048711,
  "canonical_slug": "liquid/lfm-2-24b-a2b-20260224",
  "hugging_face_id": "LiquidAI/LFM2-24B-A2B",
  "source_type": "openrouter_only",
  "context_length": 32768,
  "max_completion_tokens": null,
  "is_moderated": false,
  "architecture": {
    "modality": "text->text",
    "input_modalities": [
      "text"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
  },
  "input_modalities": [
    "text"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text->text",
  "tokenizer": "Other",
  "instruct_type": null,
  "supported_parameters": [
    "frequency_penalty",
    "logit_bias",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "repetition_penalty",
    "stop",
    "temperature",
    "top_k",
    "top_p"
  ],
  "default_parameters": {
    "temperature": 0.1,
    "top_p": null,
    "top_k": 50,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": 1.05
  },
  "per_request_limits": null,
  "top_provider": {
    "context_length": 32768,
    "max_completion_tokens": null,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.00000003",
    "completion": "0.00000012"
  },
  "PPM": {
    "prompt": 0.03,
    "completion": 0.12
  },
  "openrouter_raw": {
    "id": "liquid/lfm-2-24b-a2b",
    "canonical_slug": "liquid/lfm-2-24b-a2b-20260224",
    "hugging_face_id": "LiquidAI/LFM2-24B-A2B",
    "name": "LiquidAI: LFM2-24B-A2B",
    "created": 1772048711,
    "description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.",
    "context_length": 32768,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Other",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.00000003",
      "completion": "0.00000012"
    },
    "top_provider": {
      "context_length": 32768,
      "max_completion_tokens": null,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "logit_bias",
      "max_tokens",
      "min_p",
      "presence_penalty",
      "repetition_penalty",
      "stop",
      "temperature",
      "top_k",
      "top_p"
    ],
    "default_parameters": {
      "temperature": 0.1,
      "top_p": null,
      "top_k": 50,
      "frequency_penalty": null,
      "presence_penalty": null,
      "repetition_penalty": 1.05
    },
    "expiration_date": null
  }
}