Can I run Arete-27B on a Mac with 32 GB?
Yes, with a GGUF version
The published weights are too big, but the Q5_K_M file from bartowski/NousResearch_Arete-27B-GGUF (20.7 GB) fits, with room for ≈ 7K tokens of context.
Full analysis of Arete-27B
Everything that runs on Mac with 32 GB
Get the Q5_K_M file on Hugging Face
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q5_K_MFiles and context on Mac with 32 GB
Each file of Arete-27B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On Mac with 32 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 54.7 GB | Doesn't fit | — | — |
| BF16 | 53.8 GB | Doesn't fit | — | — |
| Q8_0 | 28.7 GB | Doesn't fit | — | — |
| Q6_K_L | 24.7 GB | Doesn't fit | — | — |
| Q6_K | 23.6 GB | Doesn't fit | — | — |
| Q6_K_S | 22.6 GB | Doesn't fit | — | — |
| Q5_K_M | 20.7 GB | Tight | 7K | 15K |
| Q5_K_S | 19.3 GB | Tight | 28K | 55K |
| Q4_K_L | 18.6 GB | Tight | 39K | 77K |
| Q4_1 | 17.6 GB | Tight | 54K | 107K |
| IQ4_NL | 17.2 GB | Tight | 59K | 118K |
| Q4_K_M | 17.2 GB | Tight | 59K | 118K |
| Q4_K_S | 16.1 GB | Fits | 75K | 151K |
| Q4_0 | 16.1 GB | Fits | 76K | 151K |
| IQ4_XS | 15.2 GB | Fits | 89K | 177K |
| IQ3_M | 14.6 GB | Fits | 98K | 195K |
| Q3_K_L | 13.9 GB | Fits | 109K | 217K |
| Q3_K_M | 13.2 GB | Fits | 119K | 239K |
| IQ3_XS | 12.6 GB | Fits | 128K | 256K |
| Q3_K_S | 12.5 GB | Fits | 129K | 256K |
| IQ3_XXS | 12.1 GB | Fits | 136K | 256K |
| Q2_K | 10.6 GB | Fits | 158K | 256K |
| IQ2_M | 10.3 GB | Fits | 162K | 256K |
| IQ2_S | 9.45 GB | Fits | 175K | 256K |
| IQ2_XS | 8.85 GB | Fits | 184K | 256K |
| IQ2_XXS | 8.64 GB | Fits | 187K | 256K |