smollamdk 3 needs about 0.8 GB of memory at Q4_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
smollamdk 3 is a 135M-parameter Smollamdk model in GGUF format, quantized by ukung. Its trained context length is 8K tokens. The repository has 1 quant file, from 0.1 GB (Q4_0) to 0.1 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.1 GB | 0.8 GB | Fits | Get file → |
What GPU do you need for smollamdk 3?
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 Q4_0 (0.1 GB file, about 0.8 GB in use).
Which smollamdk 3 quant should you choose?
Q4_0 (0.1 GB) is the middle option in this repository. 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
Source
Frequently asked questions about smollamdk 3
How much VRAM does smollamdk 3 need?
About 0.8 GB at Q4_0 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 smollamdk 3 on an 8 GB GPU?
Yes, with Q4_0: the 0.1 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of smollamdk 3 GGUF?
It depends on the quant: Q4_0 is 0.1 GB.
What context length does smollamdk 3 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download smollamdk 3 GGUF?
The files are on Hugging Face in the ukung/smollamdk-3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.