Hugging FaceA 177B, 59B active chat model from ukisai that reads pictures as well as text.
- Downloads
- 771K
- Likes
- 245
- Parameters
- 177B, 59B active
- Context
- 256K
- Licence
- other
Too big for this Mac
Its smallest size needs 68 GB of memory, more than M4 · 16 GB can give it.
Swift 1.5 Qwen3.8 Flash Next GSQ RCO runs well from a Mac with an M2 Max and 96 GB of memory. 15 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
- Qwen3.8 Flash Next Gyroagentionai · 749K downloadsToo big for this Mac · 58 GB
- POCKET Darwin 180BFINAL-Bench · 403K downloadsToo big for this Mac · 111 GB
- Swift 1.5 Qwen3.8 Flash Nextukisai · 160K downloadsToo big for this Mac · 70 GB
- Qwen3.8 Flash NextAlibaba Qwen · 9.4M downloadsToo big for this Mac · 66 GB
Sizes
From ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Q2_0 | 67 GB | 67 GBestimated | Open |
| IQ2_XS | 68 GB | 68 GBestimated | Open |
| IQ3_XXS | 76 GB | 76 GBestimated | Open |
| IQ3_S | 84 GB | 84 GBestimated | Open |
Run It Anywhere
Swift 1.5 Qwen3.8 Flash Next GSQ RCO is an open model, so any app that runs GGUF files can run it. These take the Q2_0 size from ukisai straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0 - llama.cppMac, Windows, Linux
llama-server -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0 - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 76 GB | |
| 8 GB | None worth running | needs 76 GB | |
| 10 GB | None worth running | needs 76 GB | |
| 11 GB | None worth running | needs 76 GB | |
| 12 GB | None worth running | needs 76 GB | |
| 16 GB | None worth running | needs 76 GB | |
| 20 GB | None worth running | needs 76 GB | |
| 24 GB | None worth running | needs 76 GB | |
| 32 GB | None worth running | needs 76 GB | |
| 48 GB | None worth running | needs 76 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 | Q2_0 | Too big | 68 GB | |
| M6 · 24 GB | Q2_0 | Too big | 68 GB | |
| M6 · 32 GB | Q2_0 | Too big | 68 GB | |
| M5 · 16 GB | Q2_0 | Too big | 68 GB | |
| M5 · 24 GB | Q2_0 | Too big | 68 GB | |
| M5 · 32 GB | Q2_0 | Too big | 68 GB | |
| M5 Pro · 24 GB | Q2_0 | Too big | 68 GB | |
| M5 Pro · 48 GB | Q2_0 | Too big | 68 GB | |
| M5 Pro · 64 GB | Q2_0 | Too big | 68 GB | |
| M5 Max · 36 GB | Q2_0 | Too big | 68 GB | |
| M5 Max · 48 GB | Q2_0 | Too big | 68 GB | |
| M5 Max · 64 GB | Q2_0 | Too big | 68 GB | |
| M5 Max · 128 GB | IQ2_XS | Runs great | 68 GB | 10 |
| M5 Ultra · 96 GB | IQ2_XS | Runs well | 68 GB | 20 |
| M5 Ultra · 256 GB | IQ3_S | Runs great | 85 GB | 16 |
| M5 Ultra · 512 GB | IQ3_S | Runs great | 85 GB | 16 |
| M4 · 16 GB | Q2_0 | Too big | 68 GB | |
| M4 · 24 GB | Q2_0 | Too big | 68 GB | |
| M4 · 32 GB | Q2_0 | Too big | 68 GB | |
| M4 Pro · 24 GB | Q2_0 | Too big | 68 GB | |
| M4 Pro · 48 GB | Q2_0 | Too big | 68 GB | |
| M4 Pro · 64 GB | Q2_0 | Too big | 68 GB | |
| M4 Max · 36 GB | Q2_0 | Too big | 68 GB | |
| M4 Max · 48 GB | Q2_0 | Too big | 68 GB | |
| M4 Max · 64 GB | Q2_0 | Too big | 68 GB | |
| M4 Max · 96 GB | IQ2_XS | Runs well | 68 GB | 6.7 |
| M4 Max · 128 GB | IQ2_XS | Runs great | 68 GB | 8.6 |
| M3 · 8 GB | Q2_0 | Too big | 68 GB | |
| M3 · 16 GB | Q2_0 | Too big | 68 GB | |
| M3 · 24 GB | Q2_0 | Too big | 68 GB | |
| M3 Pro · 18 GB | Q2_0 | Too big | 68 GB | |
| M3 Pro · 36 GB | Q2_0 | Too big | 68 GB | |
| M3 Max · 36 GB | Q2_0 | Too big | 68 GB | |
| M3 Max · 48 GB | Q2_0 | Too big | 68 GB | |
| M3 Max · 64 GB | Q2_0 | Too big | 68 GB | |
| M3 Max · 96 GB | IQ2_XS | Runs well | 68 GB | 5.1 |
| M3 Max · 128 GB | IQ2_XS | Runs great | 68 GB | 6.6 |
| M3 Ultra · 96 GB | IQ2_XS | Runs well | 68 GB | 12 |
| M3 Ultra · 256 GB | IQ3_S | Runs great | 85 GB | 10 |
| M3 Ultra · 512 GB | IQ3_S | Runs great | 85 GB | 10 |
| M2 · 8 GB | Q2_0 | Too big | 68 GB | |
| M2 · 16 GB | Q2_0 | Too big | 68 GB | |
| M2 · 24 GB | Q2_0 | Too big | 68 GB | |
| M2 Pro · 16 GB | Q2_0 | Too big | 68 GB | |
| M2 Pro · 32 GB | Q2_0 | Too big | 68 GB | |
| M2 Max · 32 GB | Q2_0 | Too big | 68 GB | |
| M2 Max · 64 GB | Q2_0 | Too big | 68 GB | |
| M2 Max · 96 GB | IQ2_XS | Runs well | 68 GB | 6.6 |
| M2 Ultra · 64 GB | Q2_0 | Too big | 68 GB | |
| M2 Ultra · 128 GB | IQ2_XS | Runs great | 68 GB | 12 |
| M2 Ultra · 192 GB | IQ3_S | Runs great | 85 GB | 10 |
| M1 · 8 GB | Q2_0 | Too big | 68 GB | |
| M1 · 16 GB | Q2_0 | Too big | 68 GB | |
| M1 Pro · 16 GB | Q2_0 | Too big | 68 GB | |
| M1 Pro · 32 GB | Q2_0 | Too big | 68 GB | |
| M1 Max · 32 GB | Q2_0 | Too big | 68 GB | |
| M1 Max · 64 GB | Q2_0 | Too big | 68 GB | |
| M1 Ultra · 64 GB | Q2_0 | Too big | 68 GB | |
| M1 Ultra · 128 GB | IQ2_XS | Runs great | 68 GB | 11 |
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
- ukisai
- Released
- September 2026
- Parameters
- 177B, 59B active
- Longest chat
- 256K tokens
- Reads pictures
- Yes
- Licence
- other
- Downloads this month
- 770,704
- Likes
- 245
- Sizes
- 4, 67 to 84 GB
- Kind
- Maker's release
Badge for the model card
Shows on Swift 1.5 Qwen3.8 Flash Next GSQ RCO'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.