LFM2-2.6B

by LiquidAI · built on LFM2 2.6B · Official #23 of 32 by downloads

Official2.6BSep 2025
33Kdownloads63likes

Benchmark scores

Official models are not scored on the UGI Leaderboard. We show downloads and likes instead. Estimated speed: ~12–22 tok/s (estimate), a rough range for a Q4_K_M file of this size on a recent flagship chip (Snapdragon 8 Gen 3 or A17 Pro class). It is not a measurement from this model.

About this model

LFM2-2.6B is a 2.6B-parameter language model by LiquidAI, derived from LiquidAI/LFM2-2.6B using official GGUF conversion. You can download it and run it on your phone for free.

An official 2.6B release based on LFM2 2.6B, intended for everyday chat and writing on a phone. The Q4_K_M file is 1.56 GB.

Technically, it uses the lfm2 architecture, supports a context window of 128,000 tokens (a phone will use far less).

Which RAM sizes can run it?

Device RAMiOS-safeAndroid-safe
4 GB RAMFits with Q4_K_M (~1.56 GB)Fits with Q4_K_M (~1.56 GB)
6 GB RAMFits with Q4_K_M (~1.56 GB)Fits with Q4_K_M (~1.56 GB)
8 GB RAMFits with Q4_K_M (~1.56 GB)Fits with Q4_K_M (~1.56 GB)
12 GB RAMFits with Q4_K_M (~1.56 GB)Fits with Q4_K_M (~1.56 GB)
16 GB+ RAMFits with Q4_K_M (~1.56 GB)Fits with Q4_K_M (~1.56 GB)

iOS-safe minimum: 4 GB. Android-safe minimum: 4 GB. On iOS we treat about 57% of device RAM as usable (in the 55–60% range), because the system keeps a large share and may evict an app that goes higher. On Android we treat about 67% of device RAM as usable (in the 65–70% range), leaving room for the system and the app. See the guide.

Run it on your phone

Compatible apps:

iOS

  • PocketPal AI — Free on the App Store. Can search Hugging Face and load a GGUF file on the device.
  • Layla — On the App Store as a paid app. Load a custom GGUF from files on the device.

Android

  • PocketPal AI — Free on Google Play. Can search Hugging Face and load a GGUF file on the device.
  • Layla — On Google Play. Load a custom GGUF from storage. A limited free APK is also offered on the developer site.
  • ChatterUI — Free and open source. Install the APK from the GitHub releases page. iOS is not available.

Hugging Face repository ID:

LiquidAI/LFM2-2.6B-GGUF

Recommended file: Q4_K_M — LFM2-2.6B-Q4_K_M.gguf (about 1.56 GB)

Download Q4_K_M from Hugging Face

  1. Install one of the apps above for your operating system. PocketPal AI is free on both iOS and Android and can search Hugging Face directly.
  2. In the app, add a model from Hugging Face and paste this repository ID:
    LiquidAI/LFM2-2.6B-GGUF
  3. Download the Q4_K_M file (LFM2-2.6B-Q4_K_M.gguf) (about 1.56 GB). Use wifi. This is the only step that needs internet.
  4. Load the file and start chatting. Switch on airplane mode if you like: it keeps working. A first prompt to try:
    I'm considering a decision this week. Give me the strongest case for it, the strongest case against it, and the one fact that would change my mind. Keep it short.

If the app is killed or feels slow, close other apps, try the smaller file, or pick a model with a lower iOS-safe or Android-safe minimum. On a computer, the same files work in LM Studio, Ollama and llama.cpp.

Available GGUF files (7)

QuantizationSizeDownload
Q4_0
LFM2-2.6B-Q4_0.gguf
1.48 GBDownload
Q4_K_MRECOMMENDED
LFM2-2.6B-Q4_K_M.gguf
1.56 GBDownload
Q4_K_MRECOMMENDED
LFM2-2.6B-Q4_K_M-hip-optimized.gguf
1.67 GBDownload
Q5_K_M
LFM2-2.6B-Q5_K_M.gguf
1.83 GBDownload
Q6_K
LFM2-2.6B-Q6_K.gguf
2.11 GBDownload
Q8_0
LFM2-2.6B-Q8_0.gguf
2.73 GBDownload
F16
LFM2-2.6B-F16.gguf
5.14 GBDownload

Direct downloads from LiquidAI/LFM2-2.6B-GGUF on Hugging Face. Lower Q numbers are smaller and slightly less accurate.

Similar models

Copied