Outmake Models
Models

SmolLM2 1.7B

Hugging Face · October 2024

Get Hugging Face

A 1.7B chat model from Hugging Face.

Rating
1.8
Downloads
36K
Likes
86
Parameters
1.7B
Context
8K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q8_0 size from bartowski is the one to get: a 1.8 GB download that uses 2.9 GB of memory, and writes about 9.5 words a second.

Ratings

1.8 out of 5, across people's blind votes on its answers.

Text
1115

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

SmolLM2 1.7B runs well from a Mac with an M1 and 8 GB of memory. 59 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q4_K_M1.1 GB2.1 GBestimatedOpen

Run It Anywhere

SmolLM2 1.7B is an open model, so any app that runs GGUF files can run it. These take the Q8_0 size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/SmolLM2-1.7B-Instruct-GGUF:Q8_0
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/SmolLM2-1.7B-Instruct-GGUF:Q8_0
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/SmolLM2-1.7B-Instruct-GGUF:Q8_0
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_K_M1.1 GB2.1 GB
8 GBQ4_K_M1.1 GB2.1 GB
10 GBQ4_K_M1.1 GB2.1 GB
11 GBQ4_K_M1.1 GB2.1 GB
12 GBQ4_K_M1.1 GB2.1 GB
16 GBQ4_K_M1.1 GB2.1 GB
20 GBQ4_K_M1.1 GB2.1 GB
24 GBQ4_K_M1.1 GB2.1 GB
32 GBQ4_K_M1.1 GB2.1 GB
48 GBQ4_K_M1.1 GB2.1 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac
MacSizeFitMemoryWrites
M6 · 16 GBQ8_0Runs great2.9 GB14
M6 · 24 GBQ8_0Runs great2.9 GB14
M6 · 32 GBQ8_0Runs great2.9 GB14
M5 · 16 GBQ8_0Runs great2.9 GB13
M5 · 24 GBQ8_0Runs great2.9 GB13
M5 · 32 GBQ8_0Runs great2.9 GB13
M5 Pro · 24 GBQ8_0Runs great2.9 GB25
M5 Pro · 48 GBQ8_0Runs great2.9 GB25
M5 Pro · 64 GBQ8_0Runs great2.9 GB25
M5 Max · 36 GBQ8_0Runs great2.9 GB37
M5 Max · 48 GBQ8_0Runs great2.9 GB48
M5 Max · 64 GBQ8_0Runs great2.9 GB48
M5 Max · 128 GBQ8_0Runs great2.9 GB48
M5 Ultra · 96 GBQ8_0Runs great2.9 GB91
M5 Ultra · 256 GBQ8_0Runs great2.9 GB91
M5 Ultra · 512 GBQ8_0Runs great2.9 GB91
M4 · 16 GBQ8_0Runs great2.9 GB9.5
M4 · 24 GBQ8_0Runs great2.9 GB9.5
M4 · 32 GBQ8_0Runs great2.9 GB9.5
M4 Pro · 24 GBQ8_0Runs great2.9 GB20
M4 Pro · 48 GBQ8_0Runs great2.9 GB20
M4 Pro · 64 GBQ8_0Runs great2.9 GB20
M4 Max · 36 GBQ8_0Runs great2.9 GB29
M4 Max · 48 GBQ8_0Runs great2.9 GB37
M4 Max · 64 GBQ8_0Runs great2.9 GB37
M4 Max · 96 GBQ8_0Runs great2.9 GB29
M4 Max · 128 GBQ8_0Runs great2.9 GB37
M3 · 8 GBQ8_0Runs great2.9 GB8
M3 · 16 GBQ8_0Runs great2.9 GB8
M3 · 24 GBQ8_0Runs great2.9 GB8
M3 Pro · 18 GBQ8_0Runs great2.9 GB12
M3 Pro · 36 GBQ8_0Runs great2.9 GB12
M3 Max · 36 GBQ8_0Runs great2.9 GB23
M3 Max · 48 GBQ8_0Runs great2.9 GB29
M3 Max · 64 GBQ8_0Runs great2.9 GB29
M3 Max · 96 GBQ8_0Runs great2.9 GB23
M3 Max · 128 GBQ8_0Runs great2.9 GB29
M3 Ultra · 96 GBQ8_0Runs great2.9 GB52
M3 Ultra · 256 GBQ8_0Runs great2.9 GB52
M3 Ultra · 512 GBQ8_0Runs great2.9 GB52
M2 · 8 GBQ8_0Runs great2.9 GB8
M2 · 16 GBQ8_0Runs great2.9 GB8
M2 · 24 GBQ8_0Runs great2.9 GB8
M2 Pro · 16 GBQ8_0Runs great2.9 GB16
M2 Pro · 32 GBQ8_0Runs great2.9 GB16
M2 Max · 32 GBQ8_0Runs great2.9 GB29
M2 Max · 64 GBQ8_0Runs great2.9 GB29
M2 Max · 96 GBQ8_0Runs great2.9 GB29
M2 Ultra · 64 GBQ8_0Runs great2.9 GB52
M2 Ultra · 128 GBQ8_0Runs great2.9 GB52
M2 Ultra · 192 GBQ8_0Runs great2.9 GB52
M1 · 8 GBQ8_0Runs great2.9 GB5.4
M1 · 16 GBQ8_0Runs great2.9 GB5.4
M1 Pro · 16 GBQ8_0Runs great2.9 GB15
M1 Pro · 32 GBQ8_0Runs great2.9 GB15
M1 Max · 32 GBQ8_0Runs great2.9 GB27
M1 Max · 64 GBQ8_0Runs great2.9 GB27
M1 Ultra · 64 GBQ8_0Runs great2.9 GB45
M1 Ultra · 128 GBQ8_0Runs great2.9 GB45

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Packaged by

3 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.

Information

Maker
Hugging Face
Released
October 2024
Parameters
1.7B
Longest chat
8K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
36,227
Likes
86
Sizes
1, 1.1 to 1.1 GB
Kind
Maker's release

Badge for the model card

Shows on SmolLM2 1.7B's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Runs on Mac badge

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.

Your Computer

Every model is judged for this Mac. Both are under About This Mac, in the Apple menu.

Every Mac · Every graphics card

Civitai

Open in OutmakeHugging Face

New to Outmake? Download the free beta