AI engineer | open-source AI enjoyer
-
gemma4-12b-mtp
Gemma 4 12B (QAT Q4_0) with Multi-Token Prediction speculative decoding — a fast, tool-capable local model for 16 GB - Apple Silicon Macs (~21 tok/s, ~1.4× via MTP).
tools thinking490 Pulls 1 Tag Updated 3 weeks ago
-
lfm2.5-8b-a1b
LFM2.5-8B-A1B Q8_0 with working tool calls — fixes the llama.cpp parser crash (#23838). Same weights, metadata-only fix.
tools thinking113 Pulls 2 Tags Updated 1 month ago
-
klide-8b
Agentic coding fine-tune of LFM2.5-8B-A1B for the Klide runtime — makes correct edits, verifies, and stops instead of looping. LFM Open License v1.0.
tools thinking16 Pulls 1 Tag Updated 4 days ago