Hugging FaceA 118B, 8.4B active chat model from poolside.
- Downloads
- 492K
- Likes
- 518
- Parameters
- 118B, 8.4B active
- Context
- 256K
- Licence
- openmdw-1.1
Too big for this Mac
Its smallest size needs 64 GB of memory, more than M4 · 16 GB can give it.
Laguna S 2.1 runs well from a Mac with an M1 Max and 64 GB of memory. 24 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
- Groot 65B A6B 261023GrootTeam · 13K downloadsToo big for this Mac · 56 GB
- Mistral Small 4 119B 2603Mistral AI · 46K downloadsToo big for this Mac · 27 GB
- NVIDIA Nemotron 3 Super 120B A12B BF16NVIDIA · 2.3K downloadsToo big for this Mac · 54 GB
- Mistral Large 2411Mistral AI · 35K downloadsToo big for this Mac · 28 GB
Sizes
From poolside/Laguna-S-2.1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Q4_K_M | 96 GB | 97 GBestimated | Open |
| Q8_0 | 129 GB | 130 GBestimated | Open |
| F16 | 235 GB | 236 GBestimated | Open |
Run It Anywhere
Laguna S 2.1 is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from poolside straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/poolside/Laguna-S-2.1-GGUF:Q4_K_M - llama.cppMac, Windows, Linux
llama-server -hf poolside/Laguna-S-2.1-GGUF:Q4_K_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/poolside/Laguna-S-2.1-GGUF:Q4_K_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 97 GB | |
| 8 GB | None worth running | needs 97 GB | |
| 10 GB | None worth running | needs 97 GB | |
| 11 GB | None worth running | needs 97 GB | |
| 12 GB | None worth running | needs 97 GB | |
| 16 GB | None worth running | needs 97 GB | |
| 20 GB | None worth running | needs 97 GB | |
| 24 GB | None worth running | needs 97 GB | |
| 32 GB | None worth running | needs 97 GB | |
| 48 GB | None worth running | needs 97 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 | UD-IQ1_S | Too big | 64 GB | |
| M6 · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M6 · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 Pro · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 Pro · 48 GB | UD-IQ1_M | Tight fit | 38 GB | 13 |
| M5 Pro · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 13 |
| M5 Max · 36 GB | UD-IQ1_S | Too big | 64 GB | |
| M5 Max · 48 GB | UD-IQ1_M | Tight fit | 38 GB | 25 |
| M5 Max · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 25 |
| M5 Max · 128 GB | UD-IQ4_NL | Runs great | 66 GB | 22 |
| M5 Ultra · 96 GB | UD-IQ4_NL | Runs well | 66 GB | 40 |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 159 GB | 33 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 159 GB | 33 |
| M4 · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M4 · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M4 · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M4 Pro · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M4 Pro · 48 GB | UD-IQ1_M | Tight fit | 38 GB | 11 |
| M4 Pro · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 10 |
| M4 Max · 36 GB | UD-IQ1_S | Too big | 64 GB | |
| M4 Max · 48 GB | UD-IQ1_M | Tight fit | 38 GB | 18 |
| M4 Max · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 18 |
| M4 Max · 96 GB | UD-IQ4_NL | Runs well | 66 GB | 13 |
| M4 Max · 128 GB | UD-IQ4_NL | Runs great | 66 GB | 16 |
| M3 · 8 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 Pro · 18 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 Pro · 36 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 Max · 36 GB | UD-IQ1_S | Too big | 64 GB | |
| M3 Max · 48 GB | UD-IQ1_M | Tight fit | 38 GB | 15 |
| M3 Max · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 15 |
| M3 Max · 96 GB | UD-IQ4_NL | Runs well | 66 GB | 10 |
| M3 Max · 128 GB | UD-IQ4_NL | Runs great | 66 GB | 13 |
| M3 Ultra · 96 GB | UD-IQ4_NL | Runs well | 66 GB | 22 |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 159 GB | 19 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 159 GB | 19 |
| M2 · 8 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 · 24 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 Pro · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 Pro · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 Max · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M2 Max · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 14 |
| M2 Max · 96 GB | UD-IQ4_NL | Runs well | 66 GB | 13 |
| M2 Ultra · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 24 |
| M2 Ultra · 128 GB | UD-IQ4_NL | Runs great | 66 GB | 22 |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 131 GB | 19 |
| M1 · 8 GB | UD-IQ1_S | Too big | 64 GB | |
| M1 · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M1 Pro · 16 GB | UD-IQ1_S | Too big | 64 GB | |
| M1 Pro · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M1 Max · 32 GB | UD-IQ1_S | Too big | 64 GB | |
| M1 Max · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 13 |
| M1 Ultra · 64 GB | UD-Q2_K_XL | Runs well | 42 GB | 20 |
| M1 Ultra · 128 GB | UD-IQ4_NL | Runs great | 66 GB | 18 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
4 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- poolside
- Released
- July 2026
- Parameters
- 118B, 8.4B active
- Longest chat
- 256K tokens
- Reads pictures
- No
- Licence
- openmdw-1.1
- Downloads this month
- 492,270
- Likes
- 518
- Sizes
- 3, 96 to 235 GB
- Kind
- Maker's release
- Source
- poolside/Laguna-S-2.1
Badge for the model card
Shows on Laguna S 2.1'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.