SM

SmolLM2 135M Instruct

SmolLMGGUF by lmstudio-communityUpdated 2024-10-31
Download on Hugging Face
Parameters135M
Context8K
Layers30
Architecturellama
Smallest quant0.1 GB
Quick answer

SmolLM2 135M Instruct needs about 0.8 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 (Q3_K_L) to 0.1 GB (Q8_0).

SmolLM2 135M Instruct – compact instruction‑following model

SmolLM2 135M Instruct is a 135M‑parameter language model based on the llama architecture. It supports up to 8192 tokens of context and is trained on 2 trillion tokens. The model is released under Apache‑2.0 and is available in several GGUF quantizations.

Good at

  • Instruction following
  • Text rewriting
  • Summarization

Limits

  • English‑centric
  • No vision support
  • Approx. 0.8 GB VRAM needed at 8k context

Best for

  • On‑device chat assistants
  • Lightweight code generation
  • Quick prototyping

Who it’s for. Developers and researchers needing a small, instruction‑capable model that runs on modest hardware. The model is suitable for local deployment and experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L0.1 GB 0.8 GB
Fits Get file →
Q4_K_M0.1 GB 0.8 GB
Fits Get file →
Q6_K0.1 GB 0.8 GB
Fits Get file →
Q8_00.1 GB 0.8 GB
Fits Get file →

For 8 GB VRAM or less, use Q3_K_L (0.1 GB file, 0.8 GB memory at 8k context). If you have more VRAM, Q4_K_M, Q6_K, or Q8_0 provide the same memory usage but larger file sizes. All quants use the same context length of 8192 tokens.

What GPU do you need for SmolLM2 135M 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 Q8_0 (0.1 GB file, about 0.8 GB in use).

Which SmolLM2 135M Instruct quant should you choose?

Q4_K_M is the usual starting point for SmolLM2 135M Instruct: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 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 Q3_K_L at 0.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters135M
Layers30
Trained context8,192 tokens
KV cache (fp16)23 KB per token

Source

Quantized bylmstudio-community
FamilySmolLM
Licenseapache-2.0
Downloads (HF)3,733
Last updated2024-10-31

Frequently asked questions about SmolLM2 135M Instruct

How much VRAM does SmolLM2 135M Instruct need?

About 0.8 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 SmolLM2 135M Instruct 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 SmolLM2 135M Instruct GGUF?

It depends on the quant: Q3_K_L is 0.1 GB, Q4_K_M is 0.1 GB, Q6_K is 0.1 GB, Q8_0 is 0.1 GB.

What context length does SmolLM2 135M Instruct 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 135M Instruct GGUF?

The files are on Hugging Face in the lmstudio-community/SmolLM2-135M-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 SmolLM2 135M Instruct 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 SmolLM2 135M Instruct on 8 GB VRAM?

Yes. Any quantization requires about 0.8 GB of VRAM at 8k context, well within an 8 GB budget.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Does the model support image inputs?

No. SmolLM2 135M Instruct is a text‑only model with no vision capabilities.

Other GGUFs of SmolLM2-135M-Instruct

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →