mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-12-30 22:20:20 -06:00
Code Issues Packages Projects Releases Wiki Activity

chore(model gallery): add liquidai_lfm2-8b-a1b (#6414)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-10-09 12:41:53 +02:00
committed by GitHub
parent 27c4161401
commit fcf8d41a00
1 changed files with 20 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
gallery/index.yaml
View File

@@ -424,6 +424,26 @@
- filename: LiquidAI_LFM2-350M-Math-Q4_K_M.gguf
sha256: 942e5ef43086a7a8ea5d316e819ba6a97f3829c1851cd10b87340e1b38693422
uri: huggingface://bartowski/LiquidAI_LFM2-350M-Math-GGUF/LiquidAI_LFM2-350M-Math-Q4_K_M.gguf
- !!merge <<: *lfm2
name: "liquidai_lfm2-8b-a1b"
urls:
- https://huggingface.co/LiquidAI/LFM2-8B-A1B
- https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF
description: |
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.
We're releasing the weights of our first MoE based on LFM2, with 8.3B total parameters and 1.5B active parameters.
LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B).
Code and knowledge capabilities are significantly improved compared to LFM2-2.6B.
Quantized variants fit comfortably on high-end phones, tablets, and laptops.
overrides:
parameters:
model: LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf
files:
- filename: LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf
sha256: efb59182eca2424126e9f8bde8513a1736e92d3b9a3187a2afc67968bd44512a
uri: huggingface://bartowski/LiquidAI_LFM2-8B-A1B-GGUF/LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf
- name: "kokoro"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: