Hugging FaceA 250B, 15B active chat model from Upstage.
- Rating
- 4.0
- Downloads
- 576
- Likes
- 8
- Parameters
- 250B, 15B active
- Context
- 1M
- Licence
- other
Too big for this Mac
Its smallest size needs 90 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.0 out of 5, across the tests below.
MMLU-Pro: graduate-level questions in 14 subjects. GPQA Diamond: questions PhD scientists write for each other. Humanity's Last Exam: questions written to be beyond today's models. SWE-bench Verified: real GitHub issues fixed so the project's tests pass. AIME 2026: this year's AIME competition problems. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.
Solar Open2 250B 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.
- Llama 3 1 Nemotron Ultra 253B V1NVIDIA · 2.2K downloads · Arena 1348Too big for this Mac · 54 GB
- Qwen3 235B A22B 2507Alibaba Qwen · 24K downloadsToo big for this Mac · 53 GB
- Qwen3 235B A22BAlibaba Qwen · 18K downloads · Arena 1375Too big for this Mac · 86 GB
- MiniMax M2.7MiniMax · 15K downloads · Arena 1415Too big for this Mac · 47 GB
Sizes
From prometheusAIR/Solar-Open2-250B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| IQ1_M | 60 GB | 61 GBestimated | Open |
| Q2_K | 95 GB | 96 GBestimated | Open |
| IQ4_XS | 136 GB | 137 GBestimated | Open |
| Q6_K | 206 GB | 206 GBestimated | Open |
Run It Anywhere
Solar Open2 250B is an open model, so any app that runs GGUF files can run it. These take the IQ1_M size from prometheusAIR straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/prometheusAIR/Solar-Open2-250B-GGUF:IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf prometheusAIR/Solar-Open2-250B-GGUF:IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/prometheusAIR/Solar-Open2-250B-GGUF:IQ1_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 137 GB | |
| 8 GB | None worth running | needs 137 GB | |
| 10 GB | None worth running | needs 137 GB | |
| 11 GB | None worth running | needs 137 GB | |
| 12 GB | None worth running | needs 137 GB | |
| 16 GB | None worth running | needs 137 GB | |
| 20 GB | None worth running | needs 137 GB | |
| 24 GB | None worth running | needs 137 GB | |
| 32 GB | None worth running | needs 137 GB | |
| 48 GB | None worth running | needs 137 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_M | Too big | 90 GB | |
| M6 · 24 GB | IQ1_M | Too big | 90 GB | |
| M6 · 32 GB | IQ1_M | Too big | 90 GB | |
| M5 · 16 GB | IQ1_M | Too big | 90 GB | |
| M5 · 24 GB | IQ1_M | Too big | 90 GB | |
| M5 · 32 GB | IQ1_M | Too big | 90 GB | |
| M5 Pro · 24 GB | IQ1_M | Too big | 90 GB | |
| M5 Pro · 48 GB | IQ1_M | Too big | 90 GB | |
| M5 Pro · 64 GB | IQ1_M | Too big | 90 GB | |
| M5 Max · 36 GB | IQ1_M | Too big | 90 GB | |
| M5 Max · 48 GB | IQ1_M | Too big | 90 GB | |
| M5 Max · 64 GB | IQ1_M | Too big | 90 GB | |
| M5 Max · 128 GB | Q2_K | Runs well | 99 GB | 30 |
| M5 Ultra · 96 GB | IQ1_M | Runs well | 68 GB | 69 |
| M5 Ultra · 256 GB | IQ4_XS | Runs great | 166 GB | 42 |
| M5 Ultra · 512 GB | Q6_K | Runs great | 235 GB | 33 |
| M4 · 16 GB | IQ1_M | Too big | 90 GB | |
| M4 · 24 GB | IQ1_M | Too big | 90 GB | |
| M4 · 32 GB | IQ1_M | Too big | 90 GB | |
| M4 Pro · 24 GB | IQ1_M | Too big | 90 GB | |
| M4 Pro · 48 GB | IQ1_M | Too big | 90 GB | |
| M4 Pro · 64 GB | IQ1_M | Too big | 90 GB | |
| M4 Max · 36 GB | IQ1_M | Too big | 90 GB | |
| M4 Max · 48 GB | IQ1_M | Too big | 90 GB | |
| M4 Max · 64 GB | IQ1_M | Too big | 90 GB | |
| M4 Max · 96 GB | IQ1_M | Runs well | 68 GB | 22 |
| M4 Max · 128 GB | Q2_K | Runs well | 99 GB | 21 |
| M3 · 8 GB | IQ1_M | Too big | 90 GB | |
| M3 · 16 GB | IQ1_M | Too big | 90 GB | |
| M3 · 24 GB | IQ1_M | Too big | 90 GB | |
| M3 Pro · 18 GB | IQ1_M | Too big | 90 GB | |
| M3 Pro · 36 GB | IQ1_M | Too big | 90 GB | |
| M3 Max · 36 GB | IQ1_M | Too big | 90 GB | |
| M3 Max · 48 GB | IQ1_M | Too big | 90 GB | |
| M3 Max · 64 GB | IQ1_M | Too big | 90 GB | |
| M3 Max · 96 GB | IQ1_M | Runs well | 68 GB | 18 |
| M3 Max · 128 GB | Q2_K | Runs well | 99 GB | 18 |
| M3 Ultra · 96 GB | IQ1_M | Runs well | 68 GB | 34 |
| M3 Ultra · 256 GB | IQ4_XS | Runs great | 166 GB | 23 |
| M3 Ultra · 512 GB | Q6_K | Runs great | 235 GB | 18 |
| M2 · 8 GB | IQ1_M | Too big | 90 GB | |
| M2 · 16 GB | IQ1_M | Too big | 90 GB | |
| M2 · 24 GB | IQ1_M | Too big | 90 GB | |
| M2 Pro · 16 GB | IQ1_M | Too big | 90 GB | |
| M2 Pro · 32 GB | IQ1_M | Too big | 90 GB | |
| M2 Max · 32 GB | IQ1_M | Too big | 90 GB | |
| M2 Max · 64 GB | IQ1_M | Too big | 90 GB | |
| M2 Max · 96 GB | IQ1_M | Runs well | 68 GB | 22 |
| M2 Ultra · 64 GB | IQ1_M | Too big | 90 GB | |
| M2 Ultra · 128 GB | Q2_K | Runs well | 99 GB | 28 |
| M2 Ultra · 192 GB | IQ4_XS | Runs well | 151 GB | 23 |
| M1 · 8 GB | IQ1_M | Too big | 90 GB | |
| M1 · 16 GB | IQ1_M | Too big | 90 GB | |
| M1 Pro · 16 GB | IQ1_M | Too big | 90 GB | |
| M1 Pro · 32 GB | IQ1_M | Too big | 90 GB | |
| M1 Max · 32 GB | IQ1_M | Too big | 90 GB | |
| M1 Max · 64 GB | IQ1_M | Too big | 90 GB | |
| M1 Ultra · 64 GB | IQ1_M | Too big | 90 GB | |
| M1 Ultra · 128 GB | Q2_K | Runs well | 99 GB | 22 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
3 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- Upstage
- Released
- July 2026
- Parameters
- 250B, 15B active
- Longest chat
- 1M tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 576
- Likes
- 8
- Sizes
- 4, 60 to 206 GB
- Kind
- Maker's release
- Source
- upstage/Solar-Open2-250B
Badge for the model card
Shows on Solar Open2 250B'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.