← Explore Seminal AI · AI reference · Snapshot captured September 7, 2026 · Understand model costs
Seminal AI
§1

LFM2-24B-A2B

Liquid's larger MoE for workstation-class local inference; superseded in practice by LFM2.5-8B-A1B for agentic work.

Data checked 2026-09-06

Other notable labs ga open weights LiquidAI/LFM2-24B-A2B

Context window
Max output
Input
per 1M tokens
Output
per 1M tokens
Released
2026-02-24
Parameters
24B total / 2B active (MoE)

A What it is for

B Capabilities

on-device moe
Input modalitiestext
Output modalitiestext

C Others from Other notable labs

Model Context Max out In $/M Out $/M Blended Status
Jamba Large 1.7 jamba-large-1.7 262.1K 4.1K $2.00 $8.00 $3.50 ga open
Jamba Mini 1.7 jamba-mini-1.7 256K 4.1K $0.20 $0.40 $0.25 retired open
Jamba2 Mini ai21labs/AI21-Jamba2-Mini 256K ga open
Jamba2 3B ai21labs/AI21-Jamba2-3B 256K ga open
Jamba Reasoning 3B ai21labs/AI21-Jamba-Reasoning-3B ga open
Reka Core reka-core $2.00 $6.00 $3.00 ga
Reka Flash reka-flash $0.80 $2.00 $1.10 ga
Reka Edge (reka-edge-2603) reka-edge $0.10 $0.10 $0.10 ga open
Reka Flash 3.1 RekaAI/reka-flash-3.1 ga open
Olmo 3.1 32B Think allenai/Olmo-3.1-32B-Think 65.5K 32.8K ga open
Olmo 3.1 32B Instruct allenai/Olmo-3.1-32B-Instruct 65.5K ga open
Olmo 3 32B Base allenai/Olmo-3-32B 65.5K ga open

How this model is billed. Real model: LiquidAI/LFM2-24B-A2B on Hugging Face - MoE with 24B total / 2.3B active parameters, LFM Open License v1.0, 32,768-token context, 9 languages, ~112 tok/s decode on AMD CPU and 293 tok/s on H100, sized to fit 32GB consumer RAM. No pricing on the model card and none on liquid.ai/pricing, which lists no models or token rates and instead gates use on company revenue: free to download, run

D Verify before you commit

Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.

Source: huggingface.co · checked 2026-09-06 · Other notable labs pricing · API docs