FitMyLLM
Liquid AI/Mixture of Experts

Liquid AILFM2 8B A1B

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

chattool_usemultilingual
8.3B
Parameters (1.5B active)
125K
Context length
14
Benchmarks
6
Quantizations
0
Architecture
MoE
Released
2025-11-15
Layers
24
KV Heads
8
Head Dim
64
Family
lfm

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.7 GB
5.6 + 0.1 KV
good
Q5_K_S5.57
6.4 GB
6.3 + 0.1 KV
good
Q5_K_M5.7
6.5 GB
6.4 + 0.1 KV
good
Q6_K6.56
7.4 GB
7.3 + 0.1 KV
excellent
Q8_08.5
9.4 GB
9.3 + 0.1 KV
lossless
FP1616
17.2 GB
17.1 + 0.1 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run LFM2 8B A1B now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (14)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# LFM2 8B A1B is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=LFM2-8B-A1B+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for LFM2 8B A1B

Build Hardware for LFM2 8B A1B
Spec sheet

LFM2 8B A1B — 8.3B MoE.

Specifications
Parameters
8.3B (1.5B active)
Architecture
Mixture of Experts
Context Length
125K tokens
Capabilities
chat, tool_use, multilingual
Release Date
2025-11-15
Provider
Liquid AI
Family
lfm
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.895.6 GB94%
Q5_K_S5.576.3 GB96%
Q5_K_M5.76.4 GB96%
Q6_K6.567.3 GB97%
Q8_08.59.3 GB100%
FP161617.1 GB100%
Benchmark scores
MMLU-PRO50.5
IFEval77.6
GPQA29.3
GPQA Diamond34.4
LiveCodeBench15.1
AIME25.3
HLE4.9
AA Intelligence7.0
AA Coding2.3
AA Math25.3
IFBench26.3
τ²-Bench10.5
SciCode6.8
MATH-50025.3
Compatible GPUs
30 @ Q4_K_M