SP

Speck1.1-140M-Instruct

SpeckGGUF by specklabsUpdated 2026-09-15
Download on Hugging Face
Parameters180M
Context4K
Layers18
Architecturelfm2
Smallest quant0.1 GB
Quick answer

Speck1.1-140M-Instruct needs about 1.1 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (Q4_K_M) to 0.4 GB (BF16).

Speck1.1-140M-Instruct is a 180M-parameter Speck model in GGUF format, quantized by specklabs. Its trained context length is 4K tokens. The repository has 4 quant files, from 0.1 GB (Q4_K_M) to 0.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.1 GB 0.8 GB
Fits Get file →
Q5_K_M0.1 GB 0.9 GB
Fits Get file →
Q8_00.2 GB 0.9 GB
Fits Get file →
BF160.4 GB 1.1 GB
Fits Get file →

What GPU do you need for Speck1.1-140M-Instruct?

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 BF16 (0.4 GB file, about 1.3 GB in use).

Which Speck1.1-140M-Instruct quant should you choose?

Q4_K_M is the usual starting point for Speck1.1-140M-Instruct: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.2 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
Parameters180M
Layers18
Trained context4,096 tokens
KV cache (fp16)54 KB per token

Source

Quantized byspecklabs
FamilySpeck
Licensemit
Downloads (HF)119
Last updated2026-09-15

Frequently asked questions about Speck1.1-140M-Instruct

How much VRAM does Speck1.1-140M-Instruct need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Speck1.1-140M-Instruct on an 8 GB GPU?

Yes, with BF16: the 0.4 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Speck1.1-140M-Instruct GGUF?

It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q8_0 is 0.2 GB, BF16 is 0.4 GB.

What context length does Speck1.1-140M-Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.2 GB at 4K.

Where can I download Speck1.1-140M-Instruct GGUF?

The files are on Hugging Face in the specklabs/Speck1.1-140M-Instruct-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 Speck1.1-140M-Instruct use?

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

Similar models

Browse all →

More from specklabs

All by specklabs →

More Speck models

All Speck →

Other tiny models

All tiny models →