weareapexcreators/LFM2.5-1.2B-Instruct-LocalAI

Source: 🤗🏴‍☠️ Rescued by: Alogotronmit1.2B activated1.2 GBGGUF✓ 1 checksumupdated 81d ago

CommentsShare your thoughts and shape the future of sovereign AI.

@weareapexcreators is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @weareapexcreators

Files and sources

SourceAvailable on 🤗

Checksums1 recorded

TorrentFiles match 🤗

Swarm2 seeders reported

Source revision: 9d41c2e246f2…
Witnessed: 14 Oct 2026, 13:56 UTC
Swarm checked: 15 Nov 2026, 20:01 UTC
Weight files: 1
Model size: 1.2 GB
Downloads · last month: 18,905
Publisher: Unclaimed

Weights

8-bit

Q8_01.2 GB Magnet

Speed on real hardware

LocalMaxxing

Output speed for one request at a time, measured by people running this model on their own machines.

2× RTX 3090llama.cpp · Q8_0 · 1 run492 tok/s

LD_LIBRARY_PATH=/home/beta1/qwen38-release/tools/llama-b10442-cuda /home/beta1/qwen38-release/tools/llama-b10442-cuda/llama-bench -m /mnt/pf/pf-deep2/LFM2.5-1.2B-Instruct-LocalAI/LFM2.5-1.2B-Instruct-Q8_0.gguf -p 512 -n 128 -ngl 99 -fa 1

View run on LocalMaxxing

Median of 1 community runs on 1 setups, from LocalMaxxing.

Run it yourself: setup guide