Outmake Models
Models

TinyLlama 1.1B V1.0

TinyLlama · December 2023

Get Hugging Face

A 1.1B chat model from TinyLlama.

Downloads
64K
Likes
239
Parameters
1.1B
Context
2K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q8_0 size from TheBloke is the one to get: a 1.2 GB download that uses 1.3 GB of memory, and writes about 36 words a second.

TinyLlama 1.1B V1.0 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 TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K0.5 GB0.7 GBestimatedOpen
Q3_K_S0.5 GB0.7 GBestimatedOpen
Q3_K_M0.6 GB0.8 GBestimatedOpen
Q3_K_L0.6 GB0.8 GBestimatedOpen
Q4_00.6 GB0.9 GBestimatedOpen
Q4_K_S0.6 GB0.9 GBestimatedOpen
Q4_K_M0.7 GB0.9 GBestimatedOpen
Q5_00.8 GB1.0 GBestimatedOpen
Q5_K_S0.8 GB1.0 GBestimatedOpen
Q5_K_M0.8 GB1.0 GBestimatedOpen
Q6_K0.9 GB1.1 GBestimatedOpen
Q8_01.2 GB1.4 GBestimatedOpen

Run It Anywhere

TinyLlama 1.1B V1.0 is an open model, so any app that runs GGUF files can run it. These take the Q8_0 size from TheBloke straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:Q8_0
  • llama.cppMac, Windows, Linuxllama-server -hf TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:Q8_0
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:Q8_0
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ8_01.2 GB1.4 GB
8 GBQ8_01.2 GB1.4 GB
10 GBQ8_01.2 GB1.4 GB
11 GBQ8_01.2 GB1.4 GB
12 GBQ8_01.2 GB1.4 GB
16 GBQ8_01.2 GB1.4 GB
20 GBQ8_01.2 GB1.4 GB
24 GBQ8_01.2 GB1.4 GB
32 GBQ8_01.2 GB1.4 GB
48 GBQ8_01.2 GB1.4 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 great1.3 GB56
M6 · 24 GBQ8_0Runs great1.3 GB56
M6 · 32 GBQ8_0Runs great1.3 GB56
M5 · 16 GBQ8_0Runs great1.3 GB52
M5 · 24 GBQ8_0Runs great1.3 GB52
M5 · 32 GBQ8_0Runs great1.3 GB52
M5 Pro · 24 GBQ8_0Runs great1.3 GB98
M5 Pro · 48 GBQ8_0Runs great1.3 GB98
M5 Pro · 64 GBQ8_0Runs great1.3 GB98
M5 Max · 36 GBQ8_0Runs great1.3 GB138
M5 Max · 48 GBQ8_0Runs great1.3 GB175
M5 Max · 64 GBQ8_0Runs great1.3 GB175
M5 Max · 128 GBQ8_0Runs great1.3 GB175
M5 Ultra · 96 GBQ8_0Runs great1.3 GB291
M5 Ultra · 256 GBQ8_0Runs great1.3 GB291
M5 Ultra · 512 GBQ8_0Runs great1.3 GB291
M4 · 16 GBQ8_0Runs great1.3 GB36
M4 · 24 GBQ8_0Runs great1.3 GB36
M4 · 32 GBQ8_0Runs great1.3 GB36
M4 Pro · 24 GBQ8_0Runs great1.3 GB67
M4 Pro · 48 GBQ8_0Runs great1.3 GB67
M4 Pro · 64 GBQ8_0Runs great1.3 GB67
M4 Max · 36 GBQ8_0Runs great1.3 GB88
M4 Max · 48 GBQ8_0Runs great1.3 GB103
M4 Max · 64 GBQ8_0Runs great1.3 GB103
M4 Max · 96 GBQ8_0Runs great1.3 GB88
M4 Max · 128 GBQ8_0Runs great1.3 GB103
M3 · 8 GBQ8_0Runs great1.3 GB31
M3 · 16 GBQ8_0Runs great1.3 GB31
M3 · 24 GBQ8_0Runs great1.3 GB31
M3 Pro · 18 GBQ8_0Runs great1.3 GB44
M3 Pro · 36 GBQ8_0Runs great1.3 GB44
M3 Max · 36 GBQ8_0Runs great1.3 GB76
M3 Max · 48 GBQ8_0Runs great1.3 GB92
M3 Max · 64 GBQ8_0Runs great1.3 GB92
M3 Max · 96 GBQ8_0Runs great1.3 GB76
M3 Max · 128 GBQ8_0Runs great1.3 GB92
M3 Ultra · 96 GBQ8_0Runs great1.3 GB136
M3 Ultra · 256 GBQ8_0Runs great1.3 GB136
M3 Ultra · 512 GBQ8_0Runs great1.3 GB136
M2 · 8 GBQ8_0Runs great1.3 GB31
M2 · 16 GBQ8_0Runs great1.3 GB31
M2 · 24 GBQ8_0Runs great1.3 GB31
M2 Pro · 16 GBQ8_0Runs great1.3 GB56
M2 Pro · 32 GBQ8_0Runs great1.3 GB56
M2 Max · 32 GBQ8_0Runs great1.3 GB91
M2 Max · 64 GBQ8_0Runs great1.3 GB91
M2 Max · 96 GBQ8_0Runs great1.3 GB91
M2 Ultra · 64 GBQ8_0Runs great1.3 GB134
M2 Ultra · 128 GBQ8_0Runs great1.3 GB134
M2 Ultra · 192 GBQ8_0Runs great1.3 GB134
M1 · 8 GBQ8_0Runs great1.3 GB21
M1 · 16 GBQ8_0Runs great1.3 GB21
M1 Pro · 16 GBQ8_0Runs great1.3 GB49
M1 Pro · 32 GBQ8_0Runs great1.3 GB49
M1 Max · 32 GBQ8_0Runs great1.3 GB74
M1 Max · 64 GBQ8_0Runs great1.3 GB74
M1 Ultra · 64 GBQ8_0Runs great1.3 GB100
M1 Ultra · 128 GBQ8_0Runs great1.3 GB100

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

Information

Maker
TinyLlama
Released
December 2023
Parameters
1.1B
Longest chat
2K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
64,030
Likes
239
Sizes
12, 0.5 to 1.2 GB
Kind
Maker's release

Badge for the model card

Shows on TinyLlama 1.1B V1.0'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