Models

Swift 1.5 Qwen3.8 Flash Next

ukisai · September 2026

Get

Hugging Face

A 177B, 59B active chat model from ukisai that reads pictures as well as text.

Downloads: 160K
Likes: 74
Parameters: 177B, 59B active
Context: 256K
Licence: other

Too big for this Mac

Its smallest size needs 71 GB of memory, more than M4 · 16 GB can give it.

Swift 1.5 Qwen3.8 Flash Next runs well from a Mac with an M1 Ultra and 128 GB of memory. 10 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

Size	Download	Memory at 8K	Get
IQ1_S	70 GB	70 GBestimated	Open
IQ1_M	72 GB	72 GBestimated	Open
IQ2_XXS	75 GB	75 GBestimated	Open
IQ2_XS	78 GB	78 GBestimated	Open
IQ2_S	78 GB	78 GBestimated	Open
IQ2_M	80 GB	81 GBestimated	Open
Q2_K	81 GB	81 GBestimated	Open
IQ3_XXS	88 GB	88 GBestimated	Open
Q3_K_S	89 GB	90 GBestimated	Open
IQ3_XS	92 GB	92 GBestimated	Open
Q3_K_M	92 GB	92 GBestimated	Open
Q3_K_L	93 GB	93 GBestimated	Open
IQ3_M	93 GB	93 GBestimated	Open
IQ4_XS	98 GB	98 GBestimated	Open
IQ4_NL	100 GB	100 GBestimated	Open
Q4_0	101 GB	101 GBestimated	Open
Q2_K_L	107 GB	107 GBestimated	Open
Q4_1	111 GB	111 GBestimated	Open
Q4_K_S	113 GB	113 GBestimated	Open
Q3_K_XL	119 GB	119 GBestimated	Open
Q4_K_M	120 GB	120 GBestimated	Open
Q5_K_S	128 GB	128 GBestimated	Open
Q5_K_M	135 GB	135 GBestimated	Open
Q4_K_L	139 GB	139 GBestimated	Open
Q5_K_L	151 GB	151 GBestimated	Open
Q6_K	168 GB	168 GBestimated	Open
Q8_0	188 GB	188 GBestimated	Open

Run It Anywhere

Swift 1.5 Qwen3.8 Flash Next is an open model, so any app that runs GGUF files can run it. These take the IQ1_S size from ukisai straight from Hugging Face.

LM StudioMac, Windows, LinuxOpen
JanMac, Windows, LinuxOpen
MstyMac, Windows, LinuxOpen
OllamaMac, Windows, Linuxollama run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF:IQ1_S
llama.cppMac, Windows, Linuxllama-server -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF:IQ1_S
Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF:IQ1_S

On a PC Graphics Card

Video memory	Largest size that fits	Memory at 8K
6 GB	None worth running	needs 88 GB
8 GB	None worth running	needs 88 GB
10 GB	None worth running	needs 88 GB
11 GB	None worth running	needs 88 GB
12 GB	None worth running	needs 88 GB
16 GB	None worth running	needs 88 GB
20 GB	None worth running	needs 88 GB
24 GB	None worth running	needs 88 GB
32 GB	None worth running	needs 88 GB
48 GB	None worth running	needs 88 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	IQ1_S	Too big	71 GB
M6 · 24 GB	IQ1_S	Too big	71 GB
M6 · 32 GB	IQ1_S	Too big	71 GB
M5 · 16 GB	IQ1_S	Too big	71 GB
M5 · 24 GB	IQ1_S	Too big	71 GB
M5 · 32 GB	IQ1_S	Too big	71 GB
M5 Pro · 24 GB	IQ1_S	Too big	71 GB
M5 Pro · 48 GB	IQ1_S	Too big	71 GB
M5 Pro · 64 GB	IQ1_S	Too big	71 GB
M5 Max · 36 GB	IQ1_S	Too big	71 GB
M5 Max · 48 GB	IQ1_S	Too big	71 GB
M5 Max · 64 GB	IQ1_S	Too big	71 GB
M5 Max · 128 GB	Q4_0	Runs well	101 GB	8
M5 Ultra · 96 GB	IQ2_XXS	Tight fit	76 GB	18
M5 Ultra · 256 GB	Q6_K	Runs great	169 GB	8.9
M5 Ultra · 512 GB	Q8_0	Runs great	189 GB	9.1
M4 · 16 GB	IQ1_S	Too big	71 GB
M4 · 24 GB	IQ1_S	Too big	71 GB
M4 · 32 GB	IQ1_S	Too big	71 GB
M4 Pro · 24 GB	IQ1_S	Too big	71 GB
M4 Pro · 48 GB	IQ1_S	Too big	71 GB
M4 Pro · 64 GB	IQ1_S	Too big	71 GB
M4 Max · 36 GB	IQ1_S	Too big	71 GB
M4 Max · 48 GB	IQ1_S	Too big	71 GB
M4 Max · 64 GB	IQ1_S	Too big	71 GB
M4 Max · 96 GB	IQ2_XXS	Tight fit	76 GB	6.1
M4 Max · 128 GB	Q4_0	Runs well	101 GB	6.9
M3 · 8 GB	IQ1_S	Too big	71 GB
M3 · 16 GB	IQ1_S	Too big	71 GB
M3 · 24 GB	IQ1_S	Too big	71 GB
M3 Pro · 18 GB	IQ1_S	Too big	71 GB
M3 Pro · 36 GB	IQ1_S	Too big	71 GB
M3 Max · 36 GB	IQ1_S	Too big	71 GB
M3 Max · 48 GB	IQ1_S	Too big	71 GB
M3 Max · 64 GB	IQ1_S	Too big	71 GB
M3 Max · 96 GB	IQ2_XXS	Tight fit	76 GB	4.6
M3 Max · 128 GB	Q4_0	Runs well	101 GB	5.3
M3 Ultra · 96 GB	IQ2_XXS	Tight fit	76 GB	11
M3 Ultra · 256 GB	Q6_K	Runs great	169 GB	5.5
M3 Ultra · 512 GB	Q8_0	Runs great	189 GB	5.7
M2 · 8 GB	IQ1_S	Too big	71 GB
M2 · 16 GB	IQ1_S	Too big	71 GB
M2 · 24 GB	IQ1_S	Too big	71 GB
M2 Pro · 16 GB	IQ1_S	Too big	71 GB
M2 Pro · 32 GB	IQ1_S	Too big	71 GB
M2 Max · 32 GB	IQ1_S	Too big	71 GB
M2 Max · 64 GB	IQ1_S	Too big	71 GB
M2 Max · 96 GB	IQ2_XXS	Tight fit	76 GB	6.1
M2 Ultra · 64 GB	IQ1_S	Too big	71 GB
M2 Ultra · 128 GB	Q4_0	Runs well	101 GB	9.9
M2 Ultra · 192 GB	Q5_K_S	Runs great	129 GB	7
M1 · 8 GB	IQ1_S	Too big	71 GB
M1 · 16 GB	IQ1_S	Too big	71 GB
M1 Pro · 16 GB	IQ1_S	Too big	71 GB
M1 Pro · 32 GB	IQ1_S	Too big	71 GB
M1 Max · 32 GB	IQ1_S	Too big	71 GB
M1 Max · 64 GB	IQ1_S	Too big	71 GB
M1 Ultra · 64 GB	IQ1_S	Too big	71 GB
M1 Ultra · 128 GB	Q4_0	Runs well	101 GB	9.2

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

Information

Maker: ukisai
Released: September 2026
Parameters: 177B, 59B active
Longest chat: 256K tokens
Reads pictures: Yes
Licence: other
Downloads this month: 159,577
Likes: 74
Sizes: 27, 70 to 188 GB
Kind: Maker's release
Source: ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF

Badge for the model card

Shows on Swift 1.5 Qwen3.8 Flash Next'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.