LFM2.5
Run LFM2.5 in veizik's native edge runtime on a Raspberry Pi CPU — no GPU, no Python. Weights are user-supplied from the publisher, not shipped.
- Status
- Available
- Platform
- Platform announced with the release
- Class
- Language
- Publisher
- Liquid AI
- Architecture
- lfm2
- Weights
- Supplied by you
How to run it
- Install
One package for Apple Silicon. Nothing else to install first.
step 1$ ./install.sh - Activate this device
Approve the machine in your browser; it receives a licence bound to it.
step 2$ veizik activate - Pull the checkpoint
Downloads the published safetensors into the local cache. No conversion.
step 3$ veizik pull lfm2.5-230m - Run it
One-shot, interactive, or as a local HTTP endpoint.
step 4$ veizik run lfm2.5-230m "The capital of France is" $ veizik chat lfm2.5-230m $ veizik serve lfm2.5-230m --port 8080
Where it runs.
Evidence and availability are separate: a verified device is not a download, and an available model is not verified on every device.
| Family | RTX 3080 Ti | RTX 3090 | RTX 4090 | RTX 5090 | RTX A5000 | A40 | A100 80GB PCIe | A100-SXM4-80GB | H100 80GB HBM3 | RTX PRO 4500 Blackwell | M4 Pro | M1 Ultra | M1 Max | M2 Pro |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LFM2.5 all variants | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered | —Not offered |
Availability by variant
| Model id | Availability | Platform | Context | Weights in memory |
|---|---|---|---|---|
lfm2.5-230m | Not published | Raspberry Pi · edge | — | — |
“Verified” means this family ran end to end on that exact device, on a published build. Architecture membership never upgrades a device to verified.
1 checkpoint
| Model id | Size | Modes | Checkpoint | On disk | Context | Weights in memory |
|---|---|---|---|---|---|---|
lfm2.5-230m | 230M | — | LiquidAI/LFM2.5-230M | — | — | — |
Performance
Figures publish with the release that runs it.
Weights and terms
LFM2.5 weights are published by Liquid AI under the LFM Open License v1.0 and are supplied by the user, not shipped. Commercial use is granted below US$10,000,000 annual revenue; Veizik ships only the inference engine and neither redistributes nor relicenses the weights.
Other models linked in the sidebar:
Stable Diffusion 3.5: Powered by Stability AI HunyuanImage: Weights are not included. Model availability and use are governed by the model provider's license and regional restrictions.