LocalClaw/LLM/LFM2.5-24B-A2B
Open-weight MoE

LFM2.5-24B-A2B

Use case: Reasoning. Check the memory fit and choose a setup path below.

24 GB catalogue minimum24 GB RAMQ4_K_M GGUFReasoning
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
24B (2.45B active, MoE)
Minimum RAM
24 GB
Model size
14.53 GB
Quantization
Q4_K_M GGUF

About LFM2.5-24B-A2B

Catalogue summary: Liquid AI LFM2.5 reasoning MoE built for private on-device agents. The official LFM 1.0 release has 24B total / 2.45B active parameters, 131K context, official GGUF and MLX artifacts, and a 14.5GB Q4_K_M GGUF for laptop/workstation local use.

LFM2.5-24B-A2B has a catalogue minimum of 24 GB RAM with Q4_K_M GGUF. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use LFM2.5-24B-A2B as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-11-06): LiquidAI/LFM2.5-24B-A2B-GGUFUpstream releasePaper or model cardLicence text
chatreasoningagentictool-callinglong-contextpowermoemultilingual

Install path

01
Check RAM fitMinimum 24 GB RAM. Start with the Q4_K_M GGUF quant.
02
Load the modelSearch LFM2.5-24B-A2B in LM Studio.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Download formats for this model

These are quantizations of the same model. The RAM fit above uses Q4_K_M GGUF; larger files need more memory. File sizes exclude the runtime, context cache and optional vision projector.

Catalogue record

  • Family: lfm
  • Parameters: 24B (2.45B active, MoE)
  • Recommended quantization: Q4_K_M GGUF
  • Catalogue minimum RAM: 24 GB
  • Catalogue model size: 14.53 GB
  • Tags: chat, reasoning, agentic, tool-calling, long-context, power, moe, multilingual

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
8
quality
8
coding
8
reasoning
9

Technical notes

Developer
Liquid AI
License
LFM 1.0
Context window
131,072 tokens
Architecture
Liquid AI sparse MoE reasoning model with 24B total parameters, 2.45B active parameters per token, 64 experts, top-4 routing, 30 double-gated short convolution blocks and 10 GQA layers.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

LFM3 1.7B 1.73BLFM2.5-2.6B 2.7BLFM2.5-8B-A1B 8.3B (1.5B active)LFM2.5-VL-3B 3B multimodalLFM3 VL 2B 1.92BXing4.0-29B-A4B 29B (4B active, MoE)Nex-N2.5-mini 35B MoEOccamy-1.0 35B (3B active, MoE)

Where to go next