---

license: mit

base_model: specklabs/Speck2-140M

library_name: llama.cpp

pipeline_tag: text-generation

tags:

- gguf

---

!SpeckLabs

Speck2-140M GGUF

llama.cpp-compatible GGUF builds of specklabs/Speck2-140M, pinned to

source revision 1201df613d9ee9d50909189f52e45c6fcefa3c01.

| File | Quantization | Size |

| --- | --- | ---: |

| Speck2-140M-BF16.gguf | BF16 | 361.2 MB |

| Speck2-140M-Q4_K_M.gguf | Q4_K_M | 112.9 MB |

| Speck2-140M-Q5_K_M.gguf | Q5_K_M | 130.3 MB |

| Speck2-140M-Q8_0.gguf | Q8_0 | 192.3 MB |

Usage

llama-completion -hf specklabs/Speck2-140M-GGUF:Q4_K_M -p "The meaning of life is" -n 64

The source Speck architecture and llama.cpp's LFM2 runtime implement the same alternating

attention/short-convolution operators. Conversion folds the 640-to-768 input and 768-to-640

output adapters into the embeddings, zero-pads the 384-wide convolution channels to 768, and

left-pads 3-tap causal kernels to 5 taps. These transformations preserve the model function

apart from normal floating-point and quantization rounding.

The GGUF graph stores 180,160,768 parameters because the source's tied 640-wide embedding and

two adapters become separate 768-wide input and output matrices. This compatibility transform

does not add layers or model capacity.

The conversion was built with llama.cpp revision 2e88c49c90f0add8796f633fea8c3d65b975f295. Exact checksums and

conversion provenance are in conversion.json.