---

language:

- en

- ko

- ja

- zh

license: other

license_name: lfm-open-license-v1.0

license_link: https://www.liquid.ai/lfm-license

tags:

- gguf

- lfm2

- lfm2-moe

- quantized

- apple-silicon

- ollama

- batiai

- on-device

- moe

- reasoning

- tool-calling

- edge

base_model: LiquidAI/LFM2.5-8B-A1B

pipeline_tag: text-generation

library_name: llama.cpp

---

Liquid LFM2.5-8B-A1B GGUF — Quantized by BatiAI

<p align="center">

<a href="https://flow.bati.ai"><img src="https://img.shields.io/badge/BatiFlow-macOS%20AI%20Automation-blue?style=for-the-badge&logo=apple" alt="BatiFlow"></a>

<a href="https://ollama.com/batiai/lfm2.5-8b"><img src="https://img.shields.io/badge/Ollama-batiai%2Flfm2.5--8b-green?style=for-the-badge" alt="Ollama"></a>

</p>

> Quantizations of Liquid AI LFM2.5-8B-A1B (8.3B total / 1.5B active MoE, reasoning + tool calling) for on-device AI on Mac.

> Built and verified by BatiAI for BatiFlow.

Why LFM2.5-8B-A1B?

• 8.3B total, only 1.5B active — MoE (32 experts, 4 active) gives 8B-class quality at ~1.5B-class speed
• Hybrid architecture — 24 layers: 18 double-gated LIV convolution + 6 GQA attention. Built for edge, not GPUs
• Reasoning model — explicit chain-of-thought before the final answer
• Native tool calling — Pythonic or JSON function calls (<|tool_call_start|> / <|tool_call_end|>)
• 128K context, 38T-token training budget, 128K vocab (better non-Latin tokenization incl. Korean)
• Blazing on-device — Liquid reports 253 tok/s on M5 Max, 146 tok/s on Ryzen AI Max+ 395, all under 6GB
• Released May 28, 2026

Quick Start

ollama pull batiai/lfm2.5-8b:q4

Available Quantizations

| Quant | Size | Recommended For |

|-------|------|-----------------|

| Q2_K_S | ~2.8 GB | 8GB Mac, ultra-compact (imatrix) |

| IQ3_XXS | ~3.2 GB | imatrix, smallest K-class footprint |

| Q3_K_M | ~3.9 GB | 8GB+ Mac, balanced |

| IQ4_XS | ~4.3 GB | imatrix, best size/quality |

| Q4_K_M | ~4.9 GB | 16GB Mac (recommended) |

| Q6_K | ~6.5 GB | near-original quality |

> Mac note on Q3_K_M: in every model we've benchmarked on Apple Silicon, Q3_K_M generated

> slower than Q4_K_M despite the smaller file — Granite 4.1 (+27%), Gemma 4 26B (+12%),

> Qwen3.8‑27B (+18%), Qwen3.6‑27B (+8%), on both M4 Max and M4 mini. Metal's Q3_K path is limited by

> dequantization compute rather than bandwidth. We have not measured this particular model's

> Q3/Q4 pair yet, so treat it as a strong prior, not a measurement: if Q4_K_M fits, take it.

> On CUDA the two are effectively tied, so this applies to Macs only.

Lower quants (IQ3_XXS, Q2_K_S) and imatrix variants are not provided in the official Liquid GGUF repo — BatiAI adds them for 8GB Macs and tighter footprints.

RAM Requirements

This model is tiny in active params — even the largest quant fits comfortably on 16GB. With only 1.5B active params, throughput stays high regardless of quant.

| Your Mac RAM | IQ3 | Q2 | Q3 | IQ4 | Q4 | Q6 |

|-------------|-----|-----|-----|-----|-----|-----|

| 8GB | ✅ | ✅ | ✅ | ✅ | ⚠️ | ❌ |

| 16GB | ✅ | ✅ | ✅ | ✅ | ✅ Recommended | ✅ |

| 24GB+ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |

Why BatiAI Quantization?

| | BatiAI | Official Liquid GGUF |

|---|---|---|

| Source | Official Liquid weights | Official |

| Ollama | ✅ batiai/lfm2.5-8b | ❌ HF only |

| Low quants | ✅ IQ3_XXS, Q2_K_S, Q3_K_M | ❌ Q4_0 floor |

| imatrix | ✅ IQ variants calibrated | Standard |

| Tool calling | ✅ Verified | — |

| BatiAI signed | ✅ general.author=BatiAI | — |

Technical Details

• Original Model: LiquidAI/LFM2.5-8B-A1B
• Architecture: lfm2_moe hybrid — 18 LIV conv + 6 GQA layers, 32 experts / 4 active per token
• Parameters: 8.3B total, 1.5B active
• Context: 131,072 tokens
• Training: 38T tokens
• License: LFM Open License v1.0 (Apache-2.0 based; free commercial use under $10M annual revenue)
• Quantized with: llama.cpp + imatrix
• Quantized by: BatiAI

About BatiFlow

BatiFlow — free, on-device AI automation for Mac. 5MB app, 100% local, unlimited.

License

Quantized from LiquidAI/LFM2.5-8B-A1B.

License: LFM Open License v1.0 — see https://www.liquid.ai/lfm-license. Original Liquid AI attribution retained. Free for commercial use by organizations under $10M USD annual revenue; above that threshold, contact Liquid AI.

Benchmarks

<!-- BENCH-START -->

_Benchmarks pending — measured on target Mac hardware via bench.sh._

<!-- BENCH-END -->