Hugging FaceA 69B chat model from Ai2.
- Rating
- 2.1
- Downloads
- 936
- Likes
- 6
- Parameters
- 69B
- Context
- 8K
- Licence
- other
Too big for this Mac
Its smallest size needs 31 GB of memory, more than M4 · 16 GB can give it.
Ratings
2.1 out of 5, across people's blind votes on its answers.
LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.
Tulu 2 Dpo 70B runs well from a Mac with an M3 Max and 48 GB of memory. 29 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
- Llama 2 70BTheBloke · 18K downloads · Arena 1171Too big for this Mac · 15 GB
- LongCat Flash Litemeituan-longcat · 3.6K downloadsToo big for this Mac · 33 GB
- Llama 3.3 70BMeta · 175K downloads · Arena 1318Too big for this Mac · 16 GB
- Meta Llama 3.1 70Bbartowski · 79K downloadsToo big for this Mac · 15 GB
Sizes
From TheBloke/tulu-2-dpo-70B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Q2_K | 29 GB | 31 GBestimated | Open |
| Q3_K_S | 30 GB | 32 GBestimated | Open |
| Q3_K_M | 33 GB | 35 GBestimated | Open |
| Q3_K_L | 36 GB | 38 GBestimated | Open |
| Q4_0 | 39 GB | 41 GBestimated | Open |
| Q4_K_S | 39 GB | 41 GBestimated | Open |
| Q4_K_M | 41 GB | 43 GBestimated | Open |
| Q5_0 | 47 GB | 49 GBestimated | Open |
| Q5_K_S | 47 GB | 49 GBestimated | Open |
| Q5_K_M | 49 GB | 50 GBestimated | Open |
Run It Anywhere
Tulu 2 Dpo 70B is an open model, so any app that runs GGUF files can run it. These take the Q2_K size from TheBloke straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/TheBloke/tulu-2-dpo-70B-GGUF:Q2_K - llama.cppMac, Windows, Linux
llama-server -hf TheBloke/tulu-2-dpo-70B-GGUF:Q2_K - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/TheBloke/tulu-2-dpo-70B-GGUF:Q2_K
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 32 GB | |
| 8 GB | None worth running | needs 32 GB | |
| 10 GB | None worth running | needs 32 GB | |
| 11 GB | None worth running | needs 32 GB | |
| 12 GB | None worth running | needs 32 GB | |
| 16 GB | None worth running | needs 32 GB | |
| 20 GB | None worth running | needs 32 GB | |
| 24 GB | None worth running | needs 32 GB | |
| 32 GB | Q3_K_S | 30 GB | 32 GB |
| 48 GB | Q4_K_M | 41 GB | 43 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_K | Too big | 31 GB | |
| M6 · 24 GB | Q2_K | Too big | 31 GB | |
| M6 · 32 GB | Q2_K | Too big | 31 GB | |
| M5 · 16 GB | Q2_K | Too big | 31 GB | |
| M5 · 24 GB | Q2_K | Too big | 31 GB | |
| M5 · 32 GB | Q2_K | Too big | 31 GB | |
| M5 Pro · 24 GB | Q2_K | Too big | 31 GB | |
| M5 Pro · 48 GB | Q3_K_S | Runs well | 32 GB | 4.3 |
| M5 Pro · 64 GB | Q4_K_S | Runs well | 41 GB | 3.5 |
| M5 Max · 36 GB | Q2_K | Too big | 31 GB | |
| M5 Max · 48 GB | Q3_K_S | Runs well | 32 GB | 8.4 |
| M5 Max · 64 GB | Q4_K_S | Runs well | 41 GB | 6.9 |
| M5 Max · 128 GB | Q5_K_M | Runs great | 50 GB | 5.8 |
| M5 Ultra · 96 GB | Q4_K_M | Runs great | 43 GB | 13 |
| M5 Ultra · 256 GB | Q5_K_M | Runs great | 50 GB | 11 |
| M5 Ultra · 512 GB | Q5_K_M | Runs great | 50 GB | 11 |
| M4 · 16 GB | Q2_K | Too big | 31 GB | |
| M4 · 24 GB | Q2_K | Too big | 31 GB | |
| M4 · 32 GB | Q2_K | Too big | 31 GB | |
| M4 Pro · 24 GB | Q2_K | Too big | 31 GB | |
| M4 Pro · 48 GB | Q3_K_S | Runs well | 32 GB | 3.7 |
| M4 Pro · 64 GB | Q4_K_S | Runs well | 41 GB | 3.1 |
| M4 Max · 36 GB | Q2_K | Too big | 31 GB | |
| M4 Max · 48 GB | Q3_K_S | Runs well | 32 GB | 7 |
| M4 Max · 64 GB | Q4_K_S | Runs well | 41 GB | 5.8 |
| M4 Max · 96 GB | Q4_K_M | Runs great | 43 GB | 4.3 |
| M4 Max · 128 GB | Q5_K_M | Runs great | 50 GB | 5 |
| M3 · 8 GB | Q2_K | Too big | 31 GB | |
| M3 · 16 GB | Q2_K | Too big | 31 GB | |
| M3 · 24 GB | Q2_K | Too big | 31 GB | |
| M3 Pro · 18 GB | Q2_K | Too big | 31 GB | |
| M3 Pro · 36 GB | Q2_K | Too big | 31 GB | |
| M3 Max · 36 GB | Q2_K | Too big | 31 GB | |
| M3 Max · 48 GB | Q3_K_S | Runs well | 32 GB | 5.4 |
| M3 Max · 64 GB | Q4_K_S | Runs well | 41 GB | 4.4 |
| M3 Max · 96 GB | Q4_K_M | Runs great | 43 GB | 3.2 |
| M3 Max · 128 GB | Q5_K_M | Runs great | 50 GB | 3.8 |
| M3 Ultra · 96 GB | Q4_K_M | Runs great | 43 GB | 8 |
| M3 Ultra · 256 GB | Q5_K_M | Runs great | 50 GB | 7.1 |
| M3 Ultra · 512 GB | Q5_K_M | Runs great | 50 GB | 7.1 |
| M2 · 8 GB | Q2_K | Too big | 31 GB | |
| M2 · 16 GB | Q2_K | Too big | 31 GB | |
| M2 · 24 GB | Q2_K | Too big | 31 GB | |
| M2 Pro · 16 GB | Q2_K | Too big | 31 GB | |
| M2 Pro · 32 GB | Q2_K | Too big | 31 GB | |
| M2 Max · 32 GB | Q2_K | Too big | 31 GB | |
| M2 Max · 64 GB | Q4_K_S | Runs well | 41 GB | 4.4 |
| M2 Max · 96 GB | Q4_K_M | Runs great | 43 GB | 4.3 |
| M2 Ultra · 64 GB | Q4_K_S | Runs well | 41 GB | 8.3 |
| M2 Ultra · 128 GB | Q5_K_M | Runs great | 50 GB | 7.1 |
| M2 Ultra · 192 GB | Q5_K_M | Runs great | 50 GB | 7.1 |
| M1 · 8 GB | Q2_K | Too big | 31 GB | |
| M1 · 16 GB | Q2_K | Too big | 31 GB | |
| M1 Pro · 16 GB | Q2_K | Too big | 31 GB | |
| M1 Pro · 32 GB | Q2_K | Too big | 31 GB | |
| M1 Max · 32 GB | Q2_K | Too big | 31 GB | |
| M1 Max · 64 GB | Q4_K_S | Runs well | 41 GB | 4.2 |
| M1 Ultra · 64 GB | Q4_K_S | Runs well | 41 GB | 7.6 |
| M1 Ultra · 128 GB | Q5_K_M | Runs great | 50 GB | 6.6 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- Ai2
- Released
- November 2023
- Parameters
- 69B
- Longest chat
- 8K tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 936
- Likes
- 6
- Sizes
- 10, 29 to 49 GB
- Kind
- Maker's release
- Source
- allenai/tulu-2-dpo-70b
Badge for the model card
Shows on Tulu 2 Dpo 70B'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.