Liquid AI24B (2.45B active)~15 GB VRAM at Q4_K_M

LFM2.5-24B-A2B — VRAM, speed & local setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated October 15, 2026

The largest and last LFM2.5 model: 24.0B parameters with 2.45B active per token, 40 layers of which only 10 use grouped-query attention (the other 30 are short convolutions that cache nothing), 64 experts with top-4 routing. A pure reasoning model that always thinks before answering, built for on-device agents and tool use. Text only, 131,072-token context, 16 languages including Polish and Chinese. Liquid ships official GGUF, MLX, ONNX and FP8 builds; the Q4_K_M file is 14.5 GB.

LFM2.5-24B-A2B needs about 15 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	8.8 GB	~292 tok/s	Fits
Q3_K_M 3.41 bpw	11.2 GB	~267 tok/s	Fits
Q4_K_M 4.83 bpw	15.5 GB	~232 tok/s	Fits
Q5_K_M 5.67 bpw	18 GB	~215 tok/s	Fits
Q6_K 6.56 bpw	20.7 GB	~199 tok/s	Fits
Q8_0 8.50 bpw	26.5 GB	~26 tok/s	Offload
F16 16.00 bpw	48.9 GB	~17 tok/s	Offload

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. LFM2.5-24B-A2B VRAM calculator →

Get LFM2.5-24B-A2B running

The cheapest catalogued GPU that runs LFM2.5-24B-A2B is the AMD Radeon RX 7900 XT (20 GB).

Buy this hardware AMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

AMD Radeon RX 7900 XT 20GB

20 GB VRAM · 315 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

How to run LFM2.5-24B-A2B

Install Ollama, then run:

$ollama run lfm2.5:24b

Weights on Hugging Face: LiquidAI/LFM2.5-24B-A2B-GGUF ↗

Specifications

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.

Parameters: 24.0 Billion (2.45B active)
Context window: 131,072
Architecture: Hybrid short convolution + GQA MoE (64 experts, top-4)
Provider: Liquid AI
Licence: LFM Open License v1.0
Availability: Weights downloadable
Practical deployment: Single consumer GPU
Specified at: Q4_K_M
System RAM: 32 GB
Record updated: 2026-10-15
Runs with: llama.cpp: supported source Ollama: supported source LM Studio: supported source MLX: supported source vLLM: supported source SGLang: supported source

LicenceLFM Open License v1.0Commercial use permitted

Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

Commercial use is licensed only below $10M annual revenue; above that, a separate agreement.

Limits and caveats

Always reasons before answering; there is no non-thinking mode.
Text only.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best foragentstool callingreasoningmultilingualon device

Can I run LFM2.5-24B-A2B on my GPU?

Other LFM2.5 sizes

LFM2.5-24B-A2B — frequently asked questions

How much VRAM does LFM2.5-24B-A2B need?

About 15 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does LFM2.5-24B-A2B run on an RTX 4090 (24 GB)?

Yes. LFM2.5-24B-A2B needs about 15 GB at Q4_K_M, inside a 24 GB card, at an estimated 232 tokens/sec.

How do I run LFM2.5-24B-A2B locally?

Install Ollama and run `ollama run lfm2.5:24b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does LFM2.5 come in?

LFM2.5 2.6B (2 GB), LFM2.5-8B-A1B (6 GB), LFM2.5-24B-A2B (15 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.