LLMs · Hugging Face

SmolLM 135M Instruct

Name: SmolLM 135M Instruct
Author: Hugging Face

Parameters: 0.1B
Architecture: Dense
Max context: 2K tokens
License: apache-2.0
Released: 2024-07

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run smollm:135m

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/QuantFactory/SmolLM-135M-Instruct-GGUF (opens in a new tab)

ollama run hf.co/QuantFactory/SmolLM-135M-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from Hugging Face, for fine-tuning, vLLM, Transformers.

huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization	Quality	Weights	Total at 2K context	Download
`Q2_K`	Low	0.1 GB	0.7 GB	GGUF (opens in a new tab)
`Q3_K_M`	Low	0.1 GB	0.7 GB	GGUF (opens in a new tab)
`Q4_K_M`	Good	0.1 GB	0.7 GB	GGUF (opens in a new tab)
`Q5_K_M`	High	0.1 GB	0.7 GB	GGUF (opens in a new tab)
`Q6_K`	High	0.1 GB	0.8 GB	GGUF (opens in a new tab)
`Q8_0`	Very high	0.1 GB	0.8 GB	GGUF (opens in a new tab)
`F16`	Full	0.3 GB	0.9 GB	Original weights (opens in a new tab)

Best hardware for SmolLM 135M Instruct

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at F16.

Grade · points	Hardware	Quant	Memory	Speed	Fit
44 ptsUsable (C) · 44 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	Apple M1 (16 GB)	`F16`	1.8 GB / 10.7 GB	130 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	Apple M4 (16 GB)	`F16`	1.8 GB / 10.7 GB	229 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	NVIDIA GeForce RTX 4060	`F16`	1.3 GB / 8.0 GB	603 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	Apple M4 (24 GB)	`F16`	2.2 GB / 16.1 GB	229 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	Apple M4 Pro (24 GB)	`F16`	2.2 GB / 16.1 GB	521 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	Intel Arc B580	`F16`	1.5 GB / 12.0 GB	772 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	NVIDIA GeForce RTX 3060 12GB	`F16`	1.5 GB / 12.0 GB	798 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	NVIDIA GeForce RTX 4070 SUPER	`F16`	1.5 GB / 12.0 GB	1,117 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15	AMD Radeon RX 9070 XT	`F16`	1.7 GB / 16.0 GB	1,221 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15	NVIDIA GeForce RTX 4060 Ti 16GB	`F16`	1.7 GB / 16.0 GB	638 tok/s	Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.