Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026
Model library → LFM2.5 → LFM2.5-8B-A1B
8.3B total parameters resident — about 5.8 GB at Q4_K_M, comfortable on a 6 GB card or a phone with enough RAM — with 1.5B active per token. Note the name understates it: "A1B" is a naming convention, the measured active count is 1.5B. 24 layers, 18 double-gated LIV convolution blocks plus 6 GQA attention layers, which is why its KV cache is far smaller than a 24-layer transformer's. 128K context, vocabulary widened from 65,536 to 128,000 for non-Latin scripts. LFM Open License v1.0: free for research and for commercial use below the revenue threshold the licence states.
LFM2.5-8B-A1B needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 8.3 Billion (1.5B active) |
| Context window | 131,072 |
| Architecture | Hybrid LIV convolution + GQA MoE |
| Provider | Liquid AI |
| Licence | LFM Open License v1.0 |
| Specified at | Q4_K_M |
| System RAM | 16 GB |
| Record updated | 2026-09-11 |
LFM Open License v1.0 — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 2.7 GB | 3.5 GB | ~272 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.5 GB | 4.3 GB | ~259 tok/s (est.) | Fits comfortably |
| Q4_K_M | 5.0 GB | 5.8 GB | ~237 tok/s (est.) | Fits comfortably |
| Q5_K_M | 5.9 GB | 6.7 GB | ~226 tok/s (est.) | Fits comfortably |
| Q6_K | 6.8 GB | 7.6 GB | ~215 tok/s (est.) | Fits comfortably |
| Q8_0 | 8.8 GB | 9.6 GB | ~195 tok/s (est.) | Fits comfortably |
| F16 | 16.6 GB | 17.4 GB | ~143 tok/s (est.) | Fits comfortably |
Want the memory numbers alone, at every quantization level and your own context length? Use the LFM2.5-8B-A1B VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs LFM2.5-8B-A1B is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run lfm2.5:8bWeights on Hugging Face: LiquidAI/LFM2.5-8B-A1B-GGUF.
Best for: edge devices, on device, tool use, agentic tasks.
← All LFM2.5 models | VRAM calculator | Check your own hardware