Smollm2 256x135M needs about 22.4 GB of memory at Q8_0 (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU.
Smollm2 256x135M is a 20.4B-parameter SmolLM model in GGUF format, quantized by Disya. Its trained context length is 8K tokens. The repository has 1 quant file, from 21.7 GB (Q8_0) to 21.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 21.7 GB | 22.4 GB | Too big | Get file → |
What GPU do you need for Smollm2 256x135M?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q8_0 (21.7 GB file, about 22.4 GB in use).
Which Smollm2 256x135M quant should you choose?
Q8_0 (21.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Smollm2 256x135M
How much VRAM does Smollm2 256x135M need?
About 22.4 GB at Q8_0 with an 8K context window. That is the 21.7 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 Smollm2 256x135M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Smollm2 256x135M GGUF?
It depends on the quant: Q8_0 is 21.7 GB.
What context length does Smollm2 256x135M 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 Smollm2 256x135M GGUF?
The files are on Hugging Face in the Disya/smollm2-256x135M-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.