Models

Apodex 1.1 Mini

apodex · August 2026

Get

Hugging Face

A 36B, 3.5B active chat model from apodex that reads pictures as well as text.

Downloads: 445K
Likes: 32
Parameters: 36B, 3.5B active
Context: 256K
Licence: apache-2.0

Runs well on M4 · 16 GB

The IQ2_XXS size from bartowski is the one to get: a 10 GB download that uses 11 GB of memory, and writes about 21 words a second.

Apodex 1.1 Mini runs well from a Mac with an M1 and 16 GB of memory. 56 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/apodex_Apodex-1.1-mini-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

Size	Download	Memory at 8K	Get
IQ2_XXS	10 GB	10 GBestimated	Open
IQ2_XS	11 GB	11 GBestimated	Open
IQ2_S	11 GB	12 GBestimated	Open
IQ2_M	13 GB	13 GBestimated	Open
Q2_K	13 GB	13 GBestimated	Open
Q2_K_L	14 GB	14 GBestimated	Open
IQ3_XXS	15 GB	16 GBestimated	Open
Q3_K_S	16 GB	16 GBestimated	Open
IQ3_XS	17 GB	17 GBestimated	Open
Q3_K_M	17 GB	17 GBestimated	Open
Q3_K_L	17 GB	18 GBestimated	Open
IQ3_M	17 GB	18 GBestimated	Open
Q3_K_XL	18 GB	18 GBestimated	Open
IQ4_XS	19 GB	19 GBestimated	Open
IQ4_NL	20 GB	21 GBestimated	Open
Q4_0	20 GB	21 GBestimated	Open
Q4_K_S	21 GB	21 GBestimated	Open
Q4_K_M	22 GB	22 GBestimated	Open
Q4_K_L	22 GB	22 GBestimated	Open
Q4_1	22 GB	23 GBestimated	Open
Q5_K_S	25 GB	25 GBestimated	Open
Q5_K_M	25 GB	26 GBestimated	Open
Q5_K_L	26 GB	26 GBestimated	Open
Q6_K	31 GB	31 GBestimated	Open
Q6_K_L	31 GB	31 GBestimated	Open
Q8_0	38 GB	38 GBestimated	Open
BF16	71 GB	71 GBestimated	Open

Run It Anywhere

Apodex 1.1 Mini is an open model, so any app that runs GGUF files can run it. These take the IQ2_XXS size from bartowski straight from Hugging Face.

LM StudioMac, Windows, LinuxOpen
JanMac, Windows, LinuxOpen
MstyMac, Windows, LinuxOpen
OllamaMac, Windows, Linuxollama run hf.co/bartowski/apodex_Apodex-1.1-mini-GGUF:IQ2_XXS
llama.cppMac, Windows, Linuxllama-server -hf bartowski/apodex_Apodex-1.1-mini-GGUF:IQ2_XXS
Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/apodex_Apodex-1.1-mini-GGUF:IQ2_XXS

On a PC Graphics Card

Video memory	Largest size that fits	Download	Memory at 8K
6 GB	None worth running		needs 16 GB
8 GB	None worth running		needs 16 GB
10 GB	None worth running		needs 16 GB
11 GB	None worth running		needs 16 GB
12 GB	None worth running		needs 16 GB
16 GB	IQ3_XXS	15 GB	16 GB
20 GB	IQ4_XS	19 GB	19 GB
24 GB	Q4_1	22 GB	23 GB
32 GB	Q6_K_L	31 GB	31 GB
48 GB	Q8_0	38 GB	38 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

Mac	Size	Fit	Memory	Writes
M6 · 16 GB	IQ2_XXS	Runs well	11 GB	34
M6 · 24 GB	IQ3_XXS	Runs well	16 GB	27
M6 · 32 GB	Q4_K_S	Runs well	21 GB	22
M5 · 16 GB	IQ2_XXS	Runs well	11 GB	33
M5 · 24 GB	IQ3_XXS	Runs well	16 GB	26
M5 · 32 GB	Q4_K_S	Runs well	21 GB	21
M5 Pro · 24 GB	IQ3_XXS	Runs well	16 GB	47
M5 Pro · 48 GB	Q4_1	Runs great	23 GB	42
M5 Pro · 64 GB	Q6_K	Runs great	31 GB	31
M5 Max · 36 GB	Q4_1	Runs well	23 GB	60
M5 Max · 48 GB	Q4_1	Runs great	23 GB	75
M5 Max · 64 GB	Q6_K	Runs great	31 GB	56
M5 Max · 128 GB	Q8_0	Runs great	41 GB	55
M5 Ultra · 96 GB	Q8_0	Runs great	41 GB	94
M5 Ultra · 256 GB	Q8_0	Runs great	41 GB	94
M5 Ultra · 512 GB	Q8_0	Runs great	41 GB	94
M4 · 16 GB	IQ2_XXS	Runs well	11 GB	21
M4 · 24 GB	IQ3_XXS	Runs well	16 GB	17
M4 · 32 GB	Q4_K_S	Runs well	21 GB	15
M4 Pro · 24 GB	IQ3_XXS	Runs well	16 GB	30
M4 Pro · 48 GB	Q4_1	Runs great	23 GB	29
M4 Pro · 64 GB	Q6_K	Runs great	31 GB	22
M4 Max · 36 GB	Q4_1	Runs well	23 GB	37
M4 Max · 48 GB	Q4_1	Runs great	23 GB	43
M4 Max · 64 GB	Q6_K	Runs great	31 GB	33
M4 Max · 96 GB	Q8_0	Runs great	41 GB	29
M4 Max · 128 GB	Q8_0	Runs great	41 GB	34
M3 · 8 GB	IQ1_M	Too big	12 GB
M3 · 16 GB	IQ2_XXS	Runs well	11 GB	19
M3 · 24 GB	IQ3_XXS	Runs well	16 GB	16
M3 Pro · 18 GB	IQ2_S	Runs well	12 GB	25
M3 Pro · 36 GB	Q4_1	Runs well	23 GB	20
M3 Max · 36 GB	Q4_1	Runs well	23 GB	33
M3 Max · 48 GB	Q4_1	Runs great	23 GB	39
M3 Max · 64 GB	Q6_K	Runs great	31 GB	30
M3 Max · 96 GB	Q8_0	Runs great	41 GB	24
M3 Max · 128 GB	Q8_0	Runs great	41 GB	30
M3 Ultra · 96 GB	Q8_0	Runs great	41 GB	46
M3 Ultra · 256 GB	Q8_0	Runs great	41 GB	46
M3 Ultra · 512 GB	Q8_0	Runs great	41 GB	46
M2 · 8 GB	IQ1_M	Too big	12 GB
M2 · 16 GB	IQ2_XXS	Runs well	11 GB	19
M2 · 24 GB	IQ3_XXS	Runs well	16 GB	16
M2 Pro · 16 GB	IQ2_XXS	Runs well	11 GB	31
M2 Pro · 32 GB	Q4_K_S	Runs well	21 GB	22
M2 Max · 32 GB	Q4_K_S	Runs well	21 GB	35
M2 Max · 64 GB	Q6_K	Runs great	31 GB	29
M2 Max · 96 GB	Q8_0	Runs great	41 GB	30
M2 Ultra · 64 GB	Q6_K	Runs great	31 GB	44
M2 Ultra · 128 GB	Q8_0	Runs great	41 GB	45
M2 Ultra · 192 GB	Q8_0	Runs great	41 GB	45
M1 · 8 GB	IQ1_M	Too big	12 GB
M1 · 16 GB	IQ2_XXS	Runs well	11 GB	13
M1 Pro · 16 GB	IQ2_XXS	Runs well	11 GB	25
M1 Pro · 32 GB	Q4_K_S	Runs well	21 GB	19
M1 Max · 32 GB	Q4_K_S	Runs well	21 GB	28
M1 Max · 64 GB	Q6_K	Runs great	31 GB	24
M1 Ultra · 64 GB	Q6_K	Runs great	31 GB	33
M1 Ultra · 128 GB	Q8_0	Runs great	41 GB	35

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

Packaged by

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

Information

Maker: apodex
Released: August 2026
Parameters: 36B, 3.5B active
Longest chat: 256K tokens
Reads pictures: Yes
Licence: apache-2.0
Downloads this month: 445,112
Likes: 32
Sizes: 27, 10 to 71 GB
Kind: Maker's release
Source: apodex/Apodex-1.1-mini

Badge for the model card

Shows on Apodex 1.1 Mini's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

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.