SM

SmolLM 1.7B

SmolLMGGUF by bartowskiUpdated 2024-08-20
Download on Hugging Face
Parameters1.71B
Context2K
Layers24
Architecturellama
Smallest quant0.7 GB
Quick answer

SmolLM 1.7B needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.7 GB (Q2_K) to 6.8 GB (F32).

SmolLM 1.7B Instruct model for lightweight instruction following

SmolLM 1.7B is a 1.7 billion‑parameter llama‑based model fine‑tuned for instruction following. It supports tool usage and runs with a 2048‑token context window. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Tool usage
  • Compact size

Limits

  • No vision support
  • Limited to 2048‑token context
  • Requires GPU or CPU with sufficient RAM

Best for

  • Chatbots on edge devices
  • Rapid prototyping of instruction models
  • Low‑budget inference

Who it’s for. Developers and hobbyists needing a small, instruction‑capable LLM that can run on modest hardware. The model is suitable for projects where memory constraints are critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.6 GB
Fits Get file →
IQ3_XXS0.7 GB 1.6 GB
Fits Get file →
Q2_K_L0.7 GB 1.6 GB
Fits Get file →
IQ3_XS0.7 GB 1.6 GB
Fits Get file →
IQ3_M0.8 GB 1.7 GB
Fits Get file →
Q3_K_L0.9 GB 1.8 GB
Fits Get file →
IQ4_XS0.9 GB 1.8 GB
Fits Get file →
Q3_K_XL1.0 GB 1.9 GB
Fits Get file →
Q4_K_S1.0 GB 1.9 GB
Fits Get file →
Q4_K_M1.1 GB 2.0 GB
Fits Get file →
Q4_K_L1.1 GB 2.0 GB
Fits Get file →
Q5_K_S1.2 GB 2.1 GB
Fits Get file →
Q5_K_M1.2 GB 2.1 GB
Fits Get file →
Q5_K_L1.2 GB 2.2 GB
Fits Get file →
Q6_K1.4 GB 2.3 GB
Fits Get file →
Q6_K_L1.4 GB 2.3 GB
Fits Get file →
Q8_01.8 GB 2.7 GB
Fits Get file →
F326.8 GB 7.7 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M or Q4_K_L (≈3.2 GB file, 3.2 GB memory). For 4 GB VRAM, choose Q2_K or IQ3_XXS (≈0.7 GB file, 2.8 GB memory). For CPU inference with 16 GB RAM, Q3_K_L or Q4_K_S provide a balance of size and performance.

What GPU do you need for SmolLM 1.7B?

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 (1.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.8 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (1.8 GB file, about 3.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (6.8 GB file, about 9.0 GB in use).

Which SmolLM 1.7B quant should you choose?

Q4_K_M is the usual starting point for SmolLM 1.7B: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 GB, about 1.7 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 0.7 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
Parameters1.71B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybartowski
FamilySmolLM
Licenseapache-2.0
Downloads (HF)4,753
Last updated2024-08-20

Frequently asked questions about SmolLM 1.7B

How much VRAM does SmolLM 1.7B need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 1.7B on an 8 GB GPU?

Yes, with Q8_0: the 1.8 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmolLM 1.7B GGUF?

It depends on the quant: Q2_K is 0.7 GB, IQ3_XXS is 0.7 GB, Q2_K_L is 0.7 GB, IQ3_XS is 0.7 GB, IQ3_M is 0.8 GB, Q3_K_L is 0.9 GB and 12 more.

What context length does SmolLM 1.7B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download SmolLM 1.7B GGUF?

The files are on Hugging Face in the bartowski/SmolLM-1.7B-Instruct-v0.2-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 1.7B 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 1.7B on 8 GB VRAM?

Yes, use Q4_K_M or Q4_K_L quantizations, which require about 3.2 GB of VRAM at 8k context.

Does the model support image input?

No, SmolLM 1.7B does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of SmolLM-1.7B-Instruct-v0.2

Similar models

Browse all →

More from bartowski

All by bartowski →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →