// Liquid LFM · Text LLM
LFM2-350M: VRAM & local deployment
354M parameters. About 1.0 GB at 4-bit and 1.5 GB at BF16 with one 8K-token request.
released 2025-07-10licence: Custom licence – read itmemory figures are estimates
01Specs
| Publisher | Liquid AI · LiquidAI |
|---|---|
| Family / series | Liquid LFM · LFM2 |
| Type | Text LLM (text-generation) |
| Parameters | 354M Source: counted from official safetensors weights |
| Context length | 125K tokens (128,000)max_position_embeddings in config.json |
| Architecture | 16 layers · GQA |
| Released weights | BF16 · 0.7 GBdownload |
| Licence | lfm1.0 · Custom licence – read itThe publisher uses its own licence; we have not classified it. Read the licence text. |
| Released | 2025-07-10 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Smallest GPU | Mac |
|---|---|---|---|---|---|
| BF16 / FP16 (original) | 0.7 GB | 1.6 GB | 2.4 GB | 8GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 0.4 GB | 1.2 GB | 2.0 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 0.2 GB | 1.0 GB | 1.8 GB | 8GB GPU | Mac 16GB |
KV cache per request: 8K 0.3 GB · 32K 1.1 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- llama.cpp — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from LiquidAI.
- LFM2-350M main
- LFM2-350M-GGUF GGUF
05Other Liquid LFM models
All 26 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| LFM2-700M · same series | 742M | 1.3 GB | 2025-07-10 |
| LFM2-1.2B · same series | 1.17B | 1.6 GB | 2025-07-10 |
| LFM2-2.6B · same series | 2.57B | 2.3 GB | 2025-09-22 |
| LFM2-8B-A1B · same series | 8.34B / 1B | 6.2 GB | 2025-10-07 |
| LFM2-24B-A2B · same series | 23.8B / 2B | 16.6 GB | 2026-02-24 |
| LFM2.5-24B-A2B | 24B / 2B | 16.7 GB | 2026-10-12 |
| LFM2.5-VL-3B | 3.12B | 2.7 GB | 2026-08-11 |
| LFM2.5-2.6B | 2.7B | 2.4 GB | 2026-07-28 |
| LFM2.5-Encoder-350M-Diffusion | 354M | 0.8 GB | 2026-07-10 |
| LFM2.5-230M | 230M | 0.8 GB | 2026-06-24 |
| LFM2.5-8B-A1B | 8.47B / 1B | 6.2 GB | 2026-05-28 |
| LFM2.5-1.2B-JP-202606 | 1.17B | 1.4 GB | 2026-05-26 |
| LFM2.5-ColBERT-350M | 353M | 0.7 GB | 2026-05-20 |
06Sources
Data checked 2026-08-05. Parameters, context and licence are copied from the official repository; memory figures are our estimates.