Hugging FaceA 92B, 5.8B active chat model from openpangu.
- Rating
- 3.7
- Downloads
- 3.3K
- Likes
- 11
- Parameters
- 92B, 5.8B active
- Context
- 512K
- Licence
- other
Too big for this Mac
Its smallest size needs 60 GB of memory, more than M4 · 16 GB can give it.
Ratings
3.7 out of 5, across the tests below.
GPQA Diamond: questions PhD scientists write for each other. 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.
OpenPangu 2.0 Flash 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.
- Ling Flash 2.0Ant Group · 4.8K downloads · Arena 1343Too big for this Mac · 21 GB
- C4ai Command R Plus 08 2024Cohere · 8.9K downloadsToo big for this Mac · 23 GB
- Hunyuan A13BTencent · 3.2K downloadsToo big for this Mac · 22 GB
- Qwen3 Next 80B A3BAlibaba Qwen · 133K downloads · Arena 1399Too big for this Mac · 17 GB
Sizes
From mrexodia/openPangu-2.0-Flash-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Q3_K_M | 44 GB | 44 GBestimated | Open |
| Q4_K_M | 55 GB | 56 GBestimated | Open |
| Q8_0 | 97 GB | 98 GBestimated | Open |
| BF16 | 183 GB | 184 GBestimated | Open |
Run It Anywhere
OpenPangu 2.0 Flash is an open model, so any app that runs GGUF files can run it. These take the Q3_K_M size from mrexodia straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/mrexodia/openPangu-2.0-Flash-GGUF:Q3_K_M - llama.cppMac, Windows, Linux
llama-server -hf mrexodia/openPangu-2.0-Flash-GGUF:Q3_K_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/mrexodia/openPangu-2.0-Flash-GGUF:Q3_K_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 44 GB | |
| 8 GB | None worth running | needs 44 GB | |
| 10 GB | None worth running | needs 44 GB | |
| 11 GB | None worth running | needs 44 GB | |
| 12 GB | None worth running | needs 44 GB | |
| 16 GB | None worth running | needs 44 GB | |
| 20 GB | None worth running | needs 44 GB | |
| 24 GB | None worth running | needs 44 GB | |
| 32 GB | None worth running | needs 44 GB | |
| 48 GB | Q3_K_M | 44 GB | 44 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 | Q3_K_M | Too big | 60 GB | |
| M6 · 24 GB | Q3_K_M | Too big | 60 GB | |
| M6 · 32 GB | Q3_K_M | Too big | 60 GB | |
| M5 · 16 GB | Q3_K_M | Too big | 60 GB | |
| M5 · 24 GB | Q3_K_M | Too big | 60 GB | |
| M5 · 32 GB | Q3_K_M | Too big | 60 GB | |
| M5 Pro · 24 GB | Q3_K_M | Too big | 60 GB | |
| M5 Pro · 48 GB | Q3_K_M | Too big | 60 GB | |
| M5 Pro · 64 GB | Q3_K_M | Tight fit | 48 GB | 25 |
| M5 Max · 36 GB | Q3_K_M | Too big | 60 GB | |
| M5 Max · 48 GB | Q3_K_M | Too big | 60 GB | |
| M5 Max · 64 GB | Q3_K_M | Tight fit | 48 GB | 46 |
| M5 Max · 128 GB | Q4_K_M | Runs great | 63 GB | 40 |
| M5 Ultra · 96 GB | Q4_K_M | Runs well | 63 GB | 69 |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 114 GB | 59 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 114 GB | 59 |
| M4 · 16 GB | Q3_K_M | Too big | 60 GB | |
| M4 · 24 GB | Q3_K_M | Too big | 60 GB | |
| M4 · 32 GB | Q3_K_M | Too big | 60 GB | |
| M4 Pro · 24 GB | Q3_K_M | Too big | 60 GB | |
| M4 Pro · 48 GB | Q3_K_M | Too big | 60 GB | |
| M4 Pro · 64 GB | Q3_K_M | Tight fit | 48 GB | 18 |
| M4 Max · 36 GB | Q3_K_M | Too big | 60 GB | |
| M4 Max · 48 GB | Q3_K_M | Too big | 60 GB | |
| M4 Max · 64 GB | Q3_K_M | Tight fit | 48 GB | 28 |
| M4 Max · 96 GB | Q4_K_M | Runs well | 63 GB | 22 |
| M4 Max · 128 GB | Q4_K_M | Runs great | 63 GB | 26 |
| M3 · 8 GB | Q3_K_M | Too big | 60 GB | |
| M3 · 16 GB | Q3_K_M | Too big | 60 GB | |
| M3 · 24 GB | Q3_K_M | Too big | 60 GB | |
| M3 Pro · 18 GB | Q3_K_M | Too big | 60 GB | |
| M3 Pro · 36 GB | Q3_K_M | Too big | 60 GB | |
| M3 Max · 36 GB | Q3_K_M | Too big | 60 GB | |
| M3 Max · 48 GB | Q3_K_M | Too big | 60 GB | |
| M3 Max · 64 GB | Q3_K_M | Tight fit | 48 GB | 25 |
| M3 Max · 96 GB | Q4_K_M | Runs well | 63 GB | 18 |
| M3 Max · 128 GB | Q4_K_M | Runs great | 63 GB | 23 |
| M3 Ultra · 96 GB | Q4_K_M | Runs well | 63 GB | 35 |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 114 GB | 31 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 114 GB | 31 |
| M2 · 8 GB | Q3_K_M | Too big | 60 GB | |
| M2 · 16 GB | Q3_K_M | Too big | 60 GB | |
| M2 · 24 GB | Q3_K_M | Too big | 60 GB | |
| M2 Pro · 16 GB | Q3_K_M | Too big | 60 GB | |
| M2 Pro · 32 GB | Q3_K_M | Too big | 60 GB | |
| M2 Max · 32 GB | Q3_K_M | Too big | 60 GB | |
| M2 Max · 64 GB | Q3_K_M | Tight fit | 48 GB | 25 |
| M2 Max · 96 GB | Q4_K_M | Runs well | 63 GB | 22 |
| M2 Ultra · 64 GB | Q3_K_M | Tight fit | 48 GB | 37 |
| M2 Ultra · 128 GB | Q4_K_M | Runs great | 63 GB | 34 |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 114 GB | 31 |
| M1 · 8 GB | Q3_K_M | Too big | 60 GB | |
| M1 · 16 GB | Q3_K_M | Too big | 60 GB | |
| M1 Pro · 16 GB | Q3_K_M | Too big | 60 GB | |
| M1 Pro · 32 GB | Q3_K_M | Too big | 60 GB | |
| M1 Max · 32 GB | Q3_K_M | Too big | 60 GB | |
| M1 Max · 64 GB | Q3_K_M | Tight fit | 48 GB | 20 |
| M1 Ultra · 64 GB | Q3_K_M | Tight fit | 48 GB | 28 |
| M1 Ultra · 128 GB | Q4_K_M | Runs great | 63 GB | 26 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- openpangu
- Released
- July 2026
- Parameters
- 92B, 5.8B active
- Longest chat
- 512K tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 3,257
- Likes
- 11
- Sizes
- 4, 44 to 183 GB
- Kind
- Maker's release
Badge for the model card
Shows on OpenPangu 2.0 Flash'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.