Hugging FaceA 107B, 2.1B active chat model from freriadoc.
- Downloads
- 5.7K
- Likes
- 15
- Parameters
- 107B, 2.1B active
- Context
- 256K
- Licence
- other
Too big for this Mac
Its smallest size needs 96 GB of memory, more than M4 · 16 GB can give it.
Qwen3.8 Flash Next Avalon 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.
- C4ai Command R Plus 08 2024Cohere · 8.9K downloadsToo big for this Mac · 23 GB
- Qwen1.5 110BAlibaba Qwen · 5.4K downloads · Arena 1234Too big for this Mac · 24 GB
- Ling Flash 2.0Ant Group · 4.8K downloads · Arena 1343Too big for this Mac · 21 GB
- Laguna S 2.1poolside · 492K downloadsToo big for this Mac · 34 GB
Sizes
From freriadoc/Qwen3.8-Flash-Next-Avalon-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Qwen3.8-Flash-Next-Avalon-IQ3KS | 95 GB | 95 GBestimated | Open |
Run It Anywhere
Qwen3.8 Flash Next Avalon is an open model, so any app that runs GGUF files can run it. These take the Qwen3.8-Flash-Next-Avalon-IQ3KS size from freriadoc straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/freriadoc/Qwen3.8-Flash-Next-Avalon-GGUF:Qwen3.8-Flash-Next-Avalon-IQ3KS - llama.cppMac, Windows, Linux
llama-server -hf freriadoc/Qwen3.8-Flash-Next-Avalon-GGUF:Qwen3.8-Flash-Next-Avalon-IQ3KS - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/freriadoc/Qwen3.8-Flash-Next-Avalon-GGUF:Qwen3.8-Flash-Next-Avalon-IQ3KS
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 95 GB | |
| 8 GB | None worth running | needs 95 GB | |
| 10 GB | None worth running | needs 95 GB | |
| 11 GB | None worth running | needs 95 GB | |
| 12 GB | None worth running | needs 95 GB | |
| 16 GB | None worth running | needs 95 GB | |
| 20 GB | None worth running | needs 95 GB | |
| 24 GB | None worth running | needs 95 GB | |
| 32 GB | None worth running | needs 95 GB | |
| 48 GB | None worth running | needs 95 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 | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M6 · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M6 · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Pro · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Pro · 48 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Pro · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Max · 36 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Max · 48 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Max · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Max · 128 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs well | 96 GB | 89 |
| M5 Ultra · 96 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M5 Ultra · 256 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs great | 96 GB | 135 |
| M5 Ultra · 512 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs great | 96 GB | 135 |
| M4 · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Pro · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Pro · 48 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Pro · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Max · 36 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Max · 48 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Max · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Max · 96 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M4 Max · 128 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs well | 96 GB | 45 |
| M3 · 8 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Pro · 18 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Pro · 36 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Max · 36 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Max · 48 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Max · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Max · 96 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Max · 128 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs well | 96 GB | 43 |
| M3 Ultra · 96 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M3 Ultra · 256 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs great | 96 GB | 57 |
| M3 Ultra · 512 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs great | 96 GB | 57 |
| M2 · 8 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 · 24 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Pro · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Pro · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Max · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Max · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Max · 96 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Ultra · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M2 Ultra · 128 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs well | 96 GB | 56 |
| M2 Ultra · 192 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs great | 96 GB | 56 |
| M1 · 8 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Pro · 16 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Pro · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Max · 32 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Max · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Ultra · 64 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Too big | 96 GB | |
| M1 Ultra · 128 GB | Qwen3.8-Flash-Next-Avalon-IQ3KS | Runs well | 96 GB | 39 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- freriadoc
- Released
- October 2026
- Parameters
- 107B, 2.1B active
- Longest chat
- 256K tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 5,724
- Likes
- 15
- Sizes
- 1, 95 to 95 GB
- Kind
- Maker's release
Badge for the model card
Shows on Qwen3.8 Flash Next Avalon'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.