Liquid AI · Hugging Face
LFM2.5 8B-A1B
small machinesMoE
8,5B
Parameters · 1B active
5,0 Go
Q4_K_XL file
≥ 6,5 Go
Recommended VRAM
128 000
Max context
Not measured yet
No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.
Measure my card →Which cards should it fit on?
Cards on the site whose video memory covers the recommended 6,5 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.
Technical sheet
- Published
- 2026-05-28
- Architecture
- 24 layers · 8 KV heads · dimension 64
- Attention
- Hybrid: 6 of 24 layers use standard attention, the others a fixed-memory mechanism (Mamba, linear attention) — a very light cache.
- Context cache (f16)
- ≈ 12 MB per 1,000 tokens · 0,4 Go for 32,768 tokens
- GGUF file
- unsloth/LFM2.5-8B-A1B-GGUF · LFM2.5-8B-A1B-UD-Q4_K_XL.gguf Download (5,0 Go)
- Official repo
- LiquidAI/LFM2.5-8B-A1B
Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.