SM

SmolLM2-135M

SmolLMGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters135M
Context8K
Layers30
Architecturellama
Smallest quant0.1 GB
Quick answer

SmolLM2-135M 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 3 quants, from 0.1 GB (Q4_K_M) to 0.3 GB (BF16).

SmolLM2‑135M: a compact 135M‑parameter Llama‑style model

SmolLM2‑135M is a 135M‑parameter language model based on the Llama architecture. It supports instruction following and general text generation. The model is trained on 2 trillion tokens and is lightweight enough for on‑device use.

Good at

  • Instruction following
  • General text generation
  • Lightweight deployment

Limits

  • No vision support
  • Limited to English
  • Requires 8 k context for full performance

Best for

  • On‑device chat assistants
  • Lightweight text generation
  • Embedded applications

Who it’s for. Developers needing a small, open‑source LLM for local deployment. The model is released under Apache 2.0 and can be run with llama.cpp or similar frameworks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.1 GB 0.8 GB
Fits Get file →
Q8_00.1 GB 0.8 GB
Fits Get file →
BF160.3 GB 1.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.1 GB file, ~0.8 GB memory at 8 k context). For higher precision on 16 GB VRAM, Q8_0 (0.14 GB file, ~0.8 GB memory). BF16 (0.27 GB file, ~1 GB memory) requires more VRAM but offers full precision.

What GPU do you need for SmolLM2-135M?

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 BF16 (0.3 GB file, about 1.0 GB in use).

Which SmolLM2-135M quant should you choose?

Q4_K_M is the usual starting point for SmolLM2-135M: 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.

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 byggml-org
FamilySmolLM
Licenseapache-2.0
Downloads (HF)2,237
Last updated2026-10-19

Frequently asked questions about SmolLM2-135M

How much VRAM does SmolLM2-135M 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 on an 8 GB GPU?

Yes, with BF16: the 0.3 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmolLM2-135M GGUF?

It depends on the quant: Q4_K_M is 0.1 GB, Q8_0 is 0.1 GB, BF16 is 0.3 GB.

What context length does SmolLM2-135M 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 GGUF?

The files are on Hugging Face in the ggml-org/SmolLM2-135M-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 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 on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 0.8 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

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

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of SmolLM2-135M

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →