Downloads · 30 days
123
26% of all-time downloads
Speck1.5-140M-Instruct-GGUF
specklabs/Speck1.5-140M-Instruct-GGUF
Speck1.5-140M-Instruct-GGUF is a text generation model from specklabs. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as mit.
All-time downloads
468
Public
Repo size
797 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf797 MB · 100%
At a glance
- Task
- Text Generation
- Library
- llama.cpp
- License
- mit
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Sep 15, 2026
- SHA
- 0e0631ff
Try a prompt
Base models
Model card
From the Hugging Face model README
Speck1.5-140M-Instruct GGUF
llama.cpp-compatible GGUF builds of specklabs/Speck1.5-140M-Instruct, pinned to
source revision 2b341f20dd6c8bed9955c9a11be18b302c5110ad.
| File | Quantization | Size |
|---|---|---|
| Speck1.5-140M-Instruct-BF16.gguf | BF16 | 361.2 MB |
| Speck1.5-140M-Instruct-Q4_K_M.gguf | Q4_K_M | 112.9 MB |
| Speck1.5-140M-Instruct-Q5_K_M.gguf | Q5_K_M | 130.3 MB |
| Speck1.5-140M-Instruct-Q8_0.gguf | Q8_0 | 192.4 MB |
Usage
llama-cli -hf specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M -cnv
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 180,165,376 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.
- Task
- Text Generation
- Library
- llama.cpp
- License
- mit
- Created
- Aug 30, 2026
- Updated
- Sep 15, 2026