AI Agent Hub
Back to models
LFM2.5-2.6B-ONNX logo

LFM2.5-2.6B-ONNX

Open Source LiquidAI Released 2026-08-04
11.0 / 100 2.6B params 131.1K context Open Source

About this model

Liquid AI
Try LFM • Docs • LEAP • Discord

LFM2.5-2.6B-ONNX

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-2.6B

Recommended Variants

Precision Size Platform Use Case
Q4 ~1.9 GB WebGPU, Server Recommended for most uses (quantized embedding)
Q4F16 ~1.5 GB WebGPU Quantized embedding and q4 weights with FP16 runtime and caches
FP16 ~2.1 GB WebGPU, Server Higher quality
Q8 ~2.1 GB Server only Balance of quality and size
  • WebGPU: Use Q4, Q4F16, or FP16 (Q8 is not supported on WebGPU).
  • Server (CPU/GPU): All variants supported.

Q4 and Q4F16 use a quantized input embedding. Q4F16 uses FP16 runtime tensors and caches while quantizing the LM head and decoder linear weights to q4.

Model Files

onnx/
├── model.onnx              # FP32
├── model_fp16.onnx         # FP16
├── model_q4.onnx           # Q4, quantized embedding (WebGPU)
├── model_q4f16.onnx        # Q4 embedding/weights, FP16 runtime and caches (WebGPU)
└── model_q8.onnx           # Q8

Python (onnxruntime)

pip install onnxruntime transformers numpy huggingface_hub
# or, for GPU:
pip install onnxruntime-gpu transformers numpy huggingface_hub

from huggingface_hub import hf_hub_download

model_id = "LiquidAI/LFM2.5-2.6B-ONNX"
# Q8 recommended for server CPU/GPU; use model_q4.onnx for WebGPU.
hf_hub_download(model_id, "onnx/model_q8.onnx")
hf_hub_download(model_id, "onnx/model_q8.onnx_data")

WebGPU (Transformers.js)

import { pipeline } from "@huggingface/transformers";

const generator = await pipeline("text-generation", "LiquidAI/LFM2.5-2.6B-ONNX", {
  device: "webgpu",
  dtype: "q4", // or "q4f16" or "fp16"
});

Benchmark Scores

IFEval
59.17
AIME-2025
51.87
LiveCodeBench
59.41

Technical Specs

  • Parameters: 2.6B
  • Architecture: LFM2 Hybrid
  • Context Window: 131,072 tokens
  • Input Modalities: text

Hardware Requirements

  • VRAM: 1.9 GB
  • Compute: ONNX Runtime on CPU/GPU or WebGPU; Q4 (~1.9 GB) recommended for most uses, Q4F16 (~1.5 GB) for WebGPU, FP16/Q8 (~2.1 GB) for higher quality on server