SM

SmolLM 135M

SmolLMGGUF by HuggingFaceTBUpdated 2024-08-18
Download on Hugging Face
Parameters135M
Context2K
Layers30
Architecturellama
Smallest quant0.1 GB
Quick answer

SmolLM 135M needs about 0.8 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.

SmolLM 135M – a compact instruction‑tuned LLM

SmolLM 135M is a 135M‑parameter instruction‑tuned model based on the llama architecture. It is trained on the SmolLM‑Corpus and fine‑tuned with publicly available datasets. The model supports tool usage and is available in GGUF format.

Good at

  • Tool‑enabled instruction following
  • Compact size for low‑resource inference
  • English‑only general knowledge and simple programming

Limits

  • No vision support
  • Limited to 2048 context tokens
  • English only, may struggle with complex reasoning

Best for

  • Local chatbot deployments
  • Educational content generation
  • Lightweight code assistance

Who it’s for. Developers needing a small, instruction‑tuned model for local inference. Researchers testing instruction fine‑tuning on a lightweight architecture. Hobbyists building lightweight chat applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.7 GB
Fits Get file →

The Q8_0 quantization file is 0.14 GB and requires about 0.8 GB of VRAM at 8 k context. For 8 GB VRAM, Q8_0 is suitable. If memory is tighter, consider a lower‑precision quantization, but only Q8_0 is provided here.

What GPU do you need for SmolLM 135M?

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 Q8_0 (0.1 GB file, about 0.8 GB in use).

Which SmolLM 135M quant should you choose?

Q8_0 (0.1 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

Architecturellama
Parameters135M
Layers30
Trained context2,048 tokens
KV cache (fp16)23 KB per token

Source

Quantized byHuggingFaceTB
FamilySmolLM
Licenseapache-2.0
Downloads (HF)3,340
Last updated2024-08-18

Frequently asked questions about SmolLM 135M

How much VRAM does SmolLM 135M need?

About 0.8 GB at Q8_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 SmolLM 135M on an 8 GB GPU?

Yes, with Q8_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 SmolLM 135M GGUF?

It depends on the quant: Q8_0 is 0.1 GB.

What context length does SmolLM 135M support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download SmolLM 135M GGUF?

The files are on Hugging Face in the HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-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 135M 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.

Can I run SmolLM 135M on 8 GB VRAM?

Yes, the Q8_0 quantization requires approximately 0.8 GB of VRAM at 8 k context, well within an 8 GB budget.

Does this model support vision tasks?

No, SmolLM 135M is an English‑only text model with no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of SmolLM-135M-Instruct

Similar models

Browse all →

More from HuggingFaceTB

All by HuggingFaceTB →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →