willitrun·ai

Liquid AILiquid AI

LFM2.5 8B A1B

Frontera
huggingfaceHuggingFace
116.1KDescargas658Me gustaMay 2026Publicado128K tokensContextoOtherLicencia58 BuenoCalidad

LFM2.5 8B A1B (8.5B parameters) requires approximately 6.9 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 1.5B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 8 GB of VRAM.

Comenzar

— copia y pega para ejecutar en local

Copy-paste commands to run LFM2.5 8B A1B on your machine.

Run

lms load LFM2.5-8B-A1B && lms server start

Quick specs

Parameters8.5B (1.5B active)
Architecturemoe (MoE)
Context128K tokens
Modalitytext
Min RAM3.3 GB
Rec. RAM5.2 GB (Q4_K_M)
LicenseOther
FamilyLFM2
✓ Chat

About this model

LFM2.5-8B-A1B is Liquid AI's on-device MoE assistant: 8.3B total parameters with only 1.5B activated per token (32 experts, 4 active). Its hybrid convolution + attention backbone is optimized for fast, low-memory edge inference on consumer hardware.

  • •Only ~1.5B active parameters per token — MoE efficiency for on-device use.
  • •Hybrid short-convolution + grouped-query-attention backbone (LFM2 architecture).
  • •128K context, multilingual (en, ar, zh, fr, de, ja, ko).
  • •GGUF and MLX builds recommended for llama.cpp and Apple Silicon.

Modelos relacionados

Tu hardware

Detectando...

Selecciones rápidas

Intel
Mejor económicoA
Intel Arc A580 8GB~$179 — 118 tok/s
NVIDIA
Mejor en generalA
RTX 3080 10GB~$699 — 244 tok/s

Mejor hardware

Mejores opciones para LFM2.5 8B A1B

NVIDIA
RTX 3080 10GBA
10 GB
Intel
Intel Arc B570 10GBA
10 GB
NVIDIA
GTX 1080 Ti 11GBA
11 GB
NVIDIA
RTX 2080 Ti 11GBA
11 GB
MacBook Pro M2 Pro 16GBA
16 GB

Ejecutar este modelo

LFM2.5 8B A1B on RTX 3080 10GBLFM2.5 8B A1B on Intel Arc B570 10GBLFM2.5 8B A1B on GTX 1080 Ti 11GB

Opciones de cuantización

Estimaciones de VRAM por nivel de cuantización

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
3.3 GB
Low—
Q3_K_S
3
4.2 GB
Low—
NVFP4
4
4.8 GB
Medium—
Q4_K_M
4
5.2 GB
Medium—
Q5_K_M
5
6.1 GB
High—
Q6_K
6
7.0 GB
High—
Q8_0
8
9.1 GB
Very High—
F16
16
17.4 GB
Maximum—

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

Weights5.2 GB
KV Cache0.2 GB
Runtime0.9 GB
Headroom0.6 GB

Preguntas frecuentes

FAQ — LFM2.5 8B A1B

Ver también

Guía de cuantizaciónMetodología de puntuaciónAbrir calculadora