SM

SmolLM2 135M

SmolLMGGUF by QuantFactoryUpdated 2024-11-01
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 14 quants, from 0.1 GB (Q2_K) to 0.1 GB (Q8_0).

SmolLM2 135M – a compact 135 M parameter language model

SmolLM2 135M is a 135 M parameter llama‑based model trained on 2 trillion tokens. It supports instruction following, text rewriting, summarization and function calling. The model is available in multiple quantizations for efficient deployment.

Good at

  • Instruction following
  • Text rewriting
  • Summarization

Limits

  • English‑only content
  • No vision support
  • Requires 8 k context

Best for

  • On‑device chat assistants
  • Lightweight summarization tools
  • Function‑call integration

Who it’s for. Developers needing a small, instruction‑capable model for on‑device or low‑resource deployments. The model is suitable for applications that require quick inference with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.8 GB
Fits Get file →
Q3_K_S0.1 GB 0.8 GB
Fits Get file →
Q4_00.1 GB 0.8 GB
Fits Get file →
Q3_K_M0.1 GB 0.8 GB
Fits Get file →
Q3_K_L0.1 GB 0.8 GB
Fits Get file →
Q4_10.1 GB 0.8 GB
Fits Get file →
Q4_K_S0.1 GB 0.8 GB
Fits Get file →
Q5_00.1 GB 0.8 GB
Fits Get file →
Q4_K_M0.1 GB 0.8 GB
Fits Get file →
Q5_K_S0.1 GB 0.8 GB
Fits Get file →
Q5_10.1 GB 0.8 GB
Fits Get file →
Q5_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, Q4_0 or Q4_1 (0.09–0.1 GB) provide a good balance of speed and quality. If memory is very tight, Q2_K (0.09 GB) is the smallest option. Larger quants like Q5_K_M (0.11 GB) offer higher fidelity when VRAM allows.

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 Q8_0 (0.1 GB file, about 0.8 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.

If memory is tight, the smallest file is Q2_K at 0.1 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
Parameters135M
Layers30
Trained context8,192 tokens
KV cache (fp16)23 KB per token

Source

Quantized byQuantFactory
FamilySmolLM
Licenseapache-2.0
Downloads (HF)10,636
Last updated2024-11-01

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 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 GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q4_0 is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_1 is 0.1 GB and 8 more.

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 QuantFactory/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_0 or Q4_1 quantizations use about 0.1 GB of VRAM at 8 k context, well within 8 GB.

Does the model support other languages?

The model primarily understands English; other languages may be less accurate.

Is the model licensed for commercial use?

It is released under the Apache‑2.0 license, allowing commercial deployment.

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →