LF

LFM2.5 350M home assistant sft

LfmGGUF by OrdenWillsUpdated 2026-06-28
Download on Hugging Face
Parameters353M
Context125K
Layers16
Architecturelfm2
Smallest quant0.2 GB
Quick answer

LFM2.5 350M home assistant sft needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (Q4_K_M) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

LFM2.5 350M Home Assistant – a small, tool‑oriented smart‑home model

LFM2.5 350M Home Assistant is a 350M‑parameter text‑only model fine‑tuned for smart‑home control. It supports function calling and can issue structured tool calls for lights, doors, thermostats, and media devices. The model runs on edge devices with low memory usage.

Good at

  • Structured tool calls
  • Smart‑home device control
  • Low‑memory inference

Limits

  • No vision support
  • Not suited for knowledge‑intensive tasks
  • Requires function definitions for tool use

Best for

  • Home automation assistants
  • Voice‑controlled device management
  • Low‑latency edge inference

Who it’s for. Developers building smart‑home assistants who need a lightweight model that can issue precise tool calls. The model is ideal for on‑device inference with limited VRAM and for applications that require structured outputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 1.3 GB
Fits Get file →
Q8_00.4 GB 1.4 GB
Fits Get file →
F160.7 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, the Q4_K_M quant (0.23 GB) is recommended, using about 1.3 GB of RAM at 8 k context. If higher quality is needed and 16 GB VRAM is available, Q8_0 (0.38 GB) can be used. The F16 quant (0.71 GB) is suitable for 32 GB VRAM setups.

What GPU do you need for LFM2.5 350M home assistant sft?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.7 GB file, about 1.7 GB in use).

Which LFM2.5 350M home assistant sft quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 350M home assistant sft: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters353M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized byOrdenWills
FamilyLfm
Licenseapache-2.0
Downloads (HF)1,573
Last updated2026-06-28

Frequently asked questions about LFM2.5 350M home assistant sft

How much VRAM does LFM2.5 350M home assistant sft need?

About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run LFM2.5 350M home assistant sft on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 350M home assistant sft GGUF?

It depends on the quant: Q4_K_M is 0.2 GB, Q8_0 is 0.4 GB, F16 is 0.7 GB.

What context length does LFM2.5 350M home assistant sft support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download LFM2.5 350M home assistant sft GGUF?

The files are on Hugging Face in the OrdenWills/LFM2.5-350M-home-assistant-sft repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does LFM2.5 350M home assistant sft use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run LFM2.5 350M Home Assistant on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 1.3 GB of RAM at 8 k context, fitting comfortably in 8 GB VRAM.

Does the model support image inputs?

No, it is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of LFM2.5-350M

Similar models

Browse all →

More Lfm models

All Lfm →

Other tiny models

All tiny models →