SM

smollm 350m

SmolLMGGUF by seanbailey518Updated 2024-08-18
Download on Hugging Face
Parameters362M
Context2K
Layers32
Architecturellama
Smallest quant0.2 GB
Quick answer

smollm 350m needs about 1.1 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.2 GB (Q2_K) to 0.7 GB (F16).

smollm 350m is a 362M-parameter SmolLM model in GGUF format, quantized by seanbailey518. Its trained context length is 2K tokens. The repository has 9 quant files, from 0.2 GB (Q2_K) to 0.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 0.8 GB
Fits Get file →
Q4_00.2 GB 0.8 GB
Fits Get file →
Q4_K_S0.3 GB 0.8 GB
Fits Get file →
Q5_00.3 GB 0.9 GB
Fits Get file →
Q4_K_M0.3 GB 0.9 GB
Fits Get file →
Q5_K_S0.3 GB 0.9 GB
Fits Get file →
Q5_K_M0.3 GB 0.9 GB
Fits Get file →
Q8_00.4 GB 1.0 GB
Fits Get file →
F160.7 GB 1.3 GB
Fits Get file →

What GPU do you need for smollm 350m?

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 F16 (0.7 GB file, about 1.6 GB in use).

Which smollm 350m quant should you choose?

Q4_K_M is the usual starting point for smollm 350m: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.4 GB, about 1.4 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.

If memory is tight, the smallest file is Q2_K at 0.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters362M
Layers32
Trained context2,048 tokens
KV cache (fp16)40 KB per token

Source

Quantized byseanbailey518
FamilySmolLM
Licenseapache-2.0
Downloads (HF)41
Last updated2024-08-18

Frequently asked questions about smollm 350m

How much VRAM does smollm 350m need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.3 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 smollm 350m on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of smollm 350m GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.3 GB, Q5_0 is 0.3 GB, Q4_K_M is 0.3 GB, Q5_K_S is 0.3 GB and 3 more.

What context length does smollm 350m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.

Where can I download smollm 350m GGUF?

The files are on Hugging Face in the seanbailey518/smollm-350m-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 smollm 350m use?

Hugging Face lists the license as apache-2.0. 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 seanbailey518

All by seanbailey518 →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →