LF

Spike 350M

LfmGGUF by PiecrustUpdated 2026-07-15
Download on Hugging Face
Parameters354M
Context125K
Layers16
Architecturelfm2
Smallest quant0.2 GB
Quick answer

Spike 350M 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 4 quants, from 0.2 GB (Q4_K_S) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Spike 350M is a 354M-parameter Lfm model in GGUF format, quantized by Piecrust. Its trained context length is 125K tokens. The repository has 4 quant files, from 0.2 GB (Q4_K_S) to 0.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.2 GB 1.3 GB
Fits Get file →
Q4_K_M0.2 GB 1.3 GB
Fits Get file →
Q5_K_M0.3 GB 1.3 GB
Fits Get file →
F160.7 GB 1.7 GB
Fits Get file →

What GPU do you need for Spike 350M?

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 Spike 350M quant should you choose?

Q4_K_M is the usual starting point for Spike 350M: it balances file size and quality well. Here it is a 0.2 GB file.

If memory is tight, the smallest file is Q4_K_S at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters354M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized byPiecrust
FamilyLfm
Licenseother
Downloads (HF)219
Last updated2026-07-15

Frequently asked questions about Spike 350M

How much VRAM does Spike 350M 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 Spike 350M 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 Spike 350M GGUF?

It depends on the quant: Q4_K_S is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, F16 is 0.7 GB.

What context length does Spike 350M 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 Spike 350M GGUF?

The files are on Hugging Face in the Piecrust/Spike-350M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Spike 350M use?

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

Other GGUFs of LFM2.5-350M

Similar models

Browse all →

More from Piecrust

All by Piecrust →

More Lfm models

All Lfm →

Other tiny models

All tiny models →