Hugging FaceA 104B chat model from Cohere.
- Downloads
- 8.9K
- Likes
- 27
- Parameters
- 104B
- Context
- 128K
- Licence
- cc-by-nc-4.0
Too big for this Mac
Its smallest size needs 43 GB of memory, more than M4 · 16 GB can give it.
Ratings
GPQA Diamond: questions PhD scientists write for each other. 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.
C4ai Command R Plus 08 2024 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.
- Ling Flash 2.0Ant Group · 4.8K downloads · Arena 1343Too big for this Mac · 21 GB
- Qwen3.8 Flash Next Avalonfreriadoc · 5.7K downloadsToo big for this Mac · 95 GB
- Qwen1.5 110BAlibaba Qwen · 5.4K downloads · Arena 1234Too big for this Mac · 24 GB
- Laguna S 2.1poolside · 492K downloadsToo big for this Mac · 34 GB
Sizes
From bartowski/c4ai-command-r-plus-08-2024-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| IQ1_M | 25 GB | 27 GBestimated | Open |
| IQ2_XXS | 29 GB | 30 GBestimated | Open |
| IQ2_XS | 32 GB | 33 GBestimated | Open |
| IQ2_M | 36 GB | 37 GBestimated | Open |
| Q2_K | 39 GB | 41 GBestimated | Open |
| Q2_K_L | 40 GB | 42 GBestimated | Open |
| IQ3_XXS | 41 GB | 42 GBestimated | Open |
| Q3_K_S | 46 GB | 47 GBestimated | Open |
| IQ3_M | 48 GB | 49 GBestimated | Open |
| Q3_K_M | 51 GB | 52 GBestimated | Open |
| Q3_K_L | 55 GB | 57 GBestimated | Open |
| Q3_K_XL | 56 GB | 58 GBestimated | Open |
| IQ4_XS | 56 GB | 58 GBestimated | Open |
| Q4_0_4_4 | 59 GB | 61 GBestimated | Open |
| Q4_0_4_8 | 59 GB | 61 GBestimated | Open |
| Q4_0 | 59 GB | 61 GBestimated | Open |
| Q4_K_S | 60 GB | 61 GBestimated | Open |
| Q4_K_M | 63 GB | 64 GBestimated | Open |
| Q4_K_L | 64 GB | 65 GBestimated | Open |
| Q5_K_M | 74 GB | 75 GBestimated | Open |
| Q6_K | 85 GB | 87 GBestimated | Open |
| Q8_0 | 110 GB | 112 GBestimated | Open |
Run It Anywhere
C4ai Command R Plus 08 2024 is an open model, so any app that runs GGUF files can run it. These take the IQ1_M size from bartowski straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/bartowski/c4ai-command-r-plus-08-2024-GGUF:IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf bartowski/c4ai-command-r-plus-08-2024-GGUF:IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/bartowski/c4ai-command-r-plus-08-2024-GGUF:IQ1_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 42 GB | |
| 8 GB | None worth running | needs 42 GB | |
| 10 GB | None worth running | needs 42 GB | |
| 11 GB | None worth running | needs 42 GB | |
| 12 GB | None worth running | needs 42 GB | |
| 16 GB | None worth running | needs 42 GB | |
| 20 GB | None worth running | needs 42 GB | |
| 24 GB | None worth running | needs 42 GB | |
| 32 GB | None worth running | needs 42 GB | |
| 48 GB | Q3_K_S | 46 GB | 47 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_S | Too big | 43 GB | |
| M6 · 24 GB | IQ1_S | Too big | 43 GB | |
| M6 · 32 GB | IQ1_S | Tight fit | 25 GB | 3 |
| M5 · 16 GB | IQ1_S | Too big | 43 GB | |
| M5 · 24 GB | IQ1_S | Too big | 43 GB | |
| M5 · 32 GB | IQ1_S | Tight fit | 25 GB | 2.7 |
| M5 Pro · 24 GB | IQ1_S | Too big | 43 GB | |
| M5 Pro · 48 GB | IQ2_XXS | Runs well | 31 GB | 4.7 |
| M5 Pro · 64 GB | IQ3_XXS | Runs well | 42 GB | 3.5 |
| M5 Max · 36 GB | IQ1_M | Tight fit | 28 GB | 7.6 |
| M5 Max · 48 GB | IQ2_XXS | Runs well | 31 GB | 9.2 |
| M5 Max · 64 GB | IQ3_XXS | Runs well | 42 GB | 7 |
| M5 Max · 128 GB | Q4_K_L | Runs great | 69 GB | 4.8 |
| M5 Ultra · 96 GB | Q4_K_L | Runs well | 69 GB | 9.4 |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 130 GB | 6.9 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 130 GB | 6.9 |
| M4 · 16 GB | IQ1_S | Too big | 43 GB | |
| M4 · 24 GB | IQ1_S | Too big | 43 GB | |
| M4 · 32 GB | IQ1_S | Tight fit | 25 GB | 2.2 |
| M4 Pro · 24 GB | IQ1_S | Too big | 43 GB | |
| M4 Pro · 48 GB | IQ2_XXS | Runs well | 31 GB | 4.1 |
| M4 Pro · 64 GB | IQ3_XXS | Runs well | 42 GB | 3.1 |
| M4 Max · 36 GB | IQ1_M | Tight fit | 28 GB | 6.5 |
| M4 Max · 48 GB | IQ2_XXS | Runs well | 31 GB | 7.7 |
| M4 Max · 64 GB | IQ3_XXS | Runs well | 42 GB | 6 |
| M4 Max · 96 GB | Q4_K_L | Runs well | 69 GB | 3.2 |
| M4 Max · 128 GB | Q4_K_L | Runs great | 69 GB | 4.2 |
| M3 · 8 GB | IQ1_S | Too big | 43 GB | |
| M3 · 16 GB | IQ1_S | Too big | 43 GB | |
| M3 · 24 GB | IQ1_S | Too big | 43 GB | |
| M3 Pro · 18 GB | IQ1_S | Too big | 43 GB | |
| M3 Pro · 36 GB | IQ1_M | Tight fit | 28 GB | 2.6 |
| M3 Max · 36 GB | IQ1_M | Tight fit | 28 GB | 5 |
| M3 Max · 48 GB | IQ2_XXS | Runs well | 31 GB | 5.9 |
| M3 Max · 64 GB | IQ3_XXS | Runs well | 42 GB | 4.6 |
| M3 Max · 96 GB | Q4_K_L | Runs well | 69 GB | 2.4 |
| M3 Max · 128 GB | Q4_K_L | Runs great | 69 GB | 3.2 |
| M3 Ultra · 96 GB | Q4_K_L | Runs well | 69 GB | 6.1 |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 130 GB | 4.3 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 130 GB | 4.3 |
| M2 · 8 GB | IQ1_S | Too big | 43 GB | |
| M2 · 16 GB | IQ1_S | Too big | 43 GB | |
| M2 · 24 GB | IQ1_S | Too big | 43 GB | |
| M2 Pro · 16 GB | IQ1_S | Too big | 43 GB | |
| M2 Pro · 32 GB | IQ1_S | Tight fit | 25 GB | 3.6 |
| M2 Max · 32 GB | IQ1_S | Tight fit | 25 GB | 6.8 |
| M2 Max · 64 GB | IQ3_XXS | Runs well | 42 GB | 4.5 |
| M2 Max · 96 GB | Q4_K_L | Runs well | 69 GB | 3.2 |
| M2 Ultra · 64 GB | IQ3_XXS | Runs well | 42 GB | 8.6 |
| M2 Ultra · 128 GB | Q4_K_L | Runs great | 69 GB | 6.1 |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 130 GB | 4.3 |
| M1 · 8 GB | IQ1_S | Too big | 43 GB | |
| M1 · 16 GB | IQ1_S | Too big | 43 GB | |
| M1 Pro · 16 GB | IQ1_S | Too big | 43 GB | |
| M1 Pro · 32 GB | IQ1_S | Tight fit | 25 GB | 3.5 |
| M1 Max · 32 GB | IQ1_S | Tight fit | 25 GB | 6.5 |
| M1 Max · 64 GB | IQ3_XXS | Runs well | 42 GB | 4.4 |
| M1 Ultra · 64 GB | IQ3_XXS | Runs well | 42 GB | 8 |
| M1 Ultra · 128 GB | Q4_K_L | Runs great | 69 GB | 5.8 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
2 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- Cohere
- Released
- August 2024
- Parameters
- 104B
- Longest chat
- 128K tokens
- Reads pictures
- No
- Licence
- cc-by-nc-4.0
- Downloads this month
- 8,892
- Likes
- 27
- Sizes
- 22, 25 to 110 GB
- Kind
- Maker's release
Badge for the model card
Shows on C4ai Command R Plus 08 2024'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.