Start with the ranked Mac table above, then audit tokens per second, RAM fit, quantization, runtimes, and source links before trusting the model on your Mac.
Quantizations observed: Q4_K - Medium
Quick take
Fastest published result is 229.0 tok/s on M5 Max (32-core GPU, 36 GB) at Q4_K - Medium. Published runtimes include llamafile. Start with Rankings for the decision, then use the raw rows below to audit the evidence.
Based on 63 external benchmarks; no lab runs yet.
Published runtimes: llamafile.
Model search answers
llama-3-2-1b-instruct currently has a fastest published Mac result of 229.0 tok/s on M5 Max (32-core GPU, 36 GB) at Q4_K - Medium. Check the raw rows on this page before comparing that number to a different runtime, quantization, or context length.
There is no direct best-Mac benchmark winner for llama-3-2-1b-instruct yet. Use the ranking above to find the current Apple Silicon fit path and return to this page when direct rows land.
llama-3-2-1b-instruct does not yet have a published minimum-RAM fit row on this page. Use Fit before assuming it will run cleanly on a specific Mac.
Current published coverage
Published chip coverage includes M5 Max (32-core GPU, 36 GB), M4 Max (40-core GPU, 128 GB), M4 Max (40-core GPU, 64 GB), M4 Max (40-core GPU, 48 GB), M3 Ultra (80-core GPU, 512 GB) plus 58 more chip tiers. Fastest published row is 229.0 tok/s on M5 Max (32-core GPU, 36 GB) at Q4_K - Medium.
Rows stay below the ranking because this page is answer-first. Use them to inspect exact chips, quantizations, runtimes, and sources.
| Chip | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|
| M5 Max (32-core GPU, 36 GB) | Q4_K - Medium | 229.0 tok/s | llamafile | ref |
| M4 Max (40-core GPU, 128 GB) | Q4_K - Medium | 182.6 tok/s | llamafile | ref |
| M4 Max (40-core GPU, 64 GB) | Q4_K - Medium | 180.2 tok/s | llamafile | ref |
| M4 Max (40-core GPU, 48 GB) | Q4_K - Medium | 179.0 tok/s | llamafile | ref |
| M3 Ultra (80-core GPU, 512 GB) | Q4_K - Medium | 178.8 tok/s | llamafile | ref |
| M3 Ultra (80-core GPU, 256 GB) | Q4_K - Medium | 177.9 tok/s | llamafile | ref |
| M2 Ultra (60-core GPU, 128 GB) | Q4_K - Medium | 176.4 tok/s | llamafile | ref |
| M2 Ultra (60-core GPU, 64 GB) | Q4_K - Medium | 174.1 tok/s | llamafile | ref |
| M2 Ultra (60-core GPU, 192 GB) | Q4_K - Medium | 169.8 tok/s | llamafile | ref |
| M4 Max (32-core GPU, 36 GB) | Q4_K - Medium | 166.5 tok/s | llamafile | ref |
| M4 Max (GPU count not published, 128 GB) | Q4_K - Medium | 156.3 tok/s | llamafile | ref |
| M2 Max (38-core GPU, 32 GB) | Q4_K - Medium | 153.0 tok/s | llamafile | ref |
| M1 Ultra (64-core GPU, 128 GB) | Q4_K - Medium | 151.1 tok/s | llamafile | ref |
| M3 Max (40-core GPU, 48 GB) | Q4_K - Medium | 149.0 tok/s | llamafile | ref |
| M3 Max (40-core GPU, 128 GB) | Q4_K - Medium | 146.3 tok/s | llamafile | ref |
| M1 Ultra (48-core GPU, 128 GB) | Q4_K - Medium | 138.0 tok/s | llamafile | ref |
| M3 Max (30-core GPU, 36 GB) | Q4_K - Medium | 133.0 tok/s | llamafile | ref |
| M3 Max (30-core GPU, 96 GB) | Q4_K - Medium | 132.9 tok/s | llamafile | ref |
| M2 Max (30-core GPU, 32 GB) | Q4_K - Medium | 127.6 tok/s | llamafile | ref |
| M1 Max (32-core GPU, 32 GB) | Q4_K - Medium | 125.8 tok/s | llamafile | ref |
| M1 Max (32-core GPU, 64 GB) | Q4_K - Medium | 120.7 tok/s | llamafile | ref |
| M2 Ultra (GPU count not published, 128 GB) | Q4_K - Medium | 120.4 tok/s | llamafile | ref |
| M4 Pro (20-core GPU, 24 GB) | Q4_K - Medium | 119.2 tok/s | llamafile | ref |
| M4 Pro (20-core GPU, 48 GB) | Q4_K - Medium | 118.9 tok/s | llamafile | ref |
| M4 Pro (20-core GPU, 64 GB) | Q4_K - Medium | 118.6 tok/s | llamafile | ref |
| M4 Pro (16-core GPU, 64 GB) | Q4_K - Medium | 111.9 tok/s | llamafile | ref |
| M4 Pro (16-core GPU, 48 GB) | Q4_K - Medium | 111.0 tok/s | llamafile | ref |
| M4 Pro (16-core GPU, 24 GB) | Q4_K - Medium | 110.9 tok/s | llamafile | ref |
| M3 Max (40-core GPU, 64 GB) | Q4_K - Medium | 107.0 tok/s | llamafile | ref |
| M1 Max (24-core GPU, 64 GB) | Q4_K - Medium | 105.7 tok/s | llamafile | ref |
| M2 Pro (19-core GPU, 32 GB) | Q4_K - Medium | 100.3 tok/s | llamafile | ref |
| M2 Pro (19-core GPU, 16 GB) | Q4_K - Medium | 99.5 tok/s | llamafile | ref |
| M5 (10-core GPU, 32 GB) | Q4_K - Medium | 98.4 tok/s | llamafile | ref |
| M5 (10-core GPU, 16 GB) | Q4_K - Medium | 98.1 tok/s | llamafile | ref |
| M1 Max (24-core GPU, 32 GB) | Q4_K - Medium | 93.9 tok/s | llamafile | ref |
| M2 Pro (16-core GPU, 32 GB) | Q4_K - Medium | 91.5 tok/s | llamafile | ref |
| M2 Pro (16-core GPU, 16 GB) | Q4_K - Medium | 91.1 tok/s | llamafile | ref |
| M3 Pro (18-core GPU, 36 GB) | Q4_K - Medium | 89.8 tok/s | llamafile | ref |
| M3 Pro (14-core GPU, 36 GB) | Q4_K - Medium | 88.2 tok/s | llamafile | ref |
| M3 Pro (14-core GPU, 18 GB) | Q4_K - Medium | 88.1 tok/s | llamafile | ref |
| M3 Pro (18-core GPU, 18 GB) | Q4_K - Medium | 85.6 tok/s | llamafile | ref |
| M1 Pro (16-core GPU, 16 GB) | Q4_K - Medium | 78.2 tok/s | llamafile | ref |
| M1 Pro (16-core GPU, 32 GB) | Q4_K - Medium | 77.2 tok/s | llamafile | ref |
| M4 (10-core GPU, 16 GB) | Q4_K - Medium | 76.2 tok/s | llamafile | ref |
| M4 (10-core GPU, 32 GB) | Q4_K - Medium | 75.6 tok/s | llamafile | ref |
| M4 (10-core GPU, 24 GB) | Q4_K - Medium | 75.4 tok/s | llamafile | ref |
| M1 Pro (14-core GPU, 16 GB) | Q4_K - Medium | 71.8 tok/s | llamafile | ref |
| M1 Pro (14-core GPU, 32 GB) | Q4_K - Medium | 71.0 tok/s | llamafile | ref |
| M4 (GPU count not published, 16 GB) | Q4_K - Medium | 68.0 tok/s | llamafile | ref |
| M3 (10-core GPU, 16 GB) | Q4_K - Medium | 67.2 tok/s | llamafile | ref |
| M4 (8-core GPU, 16 GB) | Q4_K - Medium | 65.9 tok/s | llamafile | ref |
| M3 (10-core GPU, 24 GB) | Q4_K - Medium | 64.7 tok/s | llamafile | ref |
| M3 (GPU count not published, 16 GB) | Q4_K - Medium | 61.6 tok/s | llamafile | ref |
| M1 Ultra (GPU count not published, 128 GB) | Q4_K - Medium | 57.1 tok/s | llamafile | ref |
| M2 (10-core GPU, 8 GB) | Q4_K - Medium | 56.5 tok/s | llamafile | ref |
| M2 (10-core GPU, 16 GB) | Q4_K - Medium | 55.6 tok/s | llamafile | ref |
| M2 (10-core GPU, 24 GB) | Q4_K - Medium | 54.8 tok/s | llamafile | ref |
| M1 (8-core GPU, 8 GB) | Q4_K - Medium | 40.4 tok/s | llamafile | ref |
| M1 (8-core GPU, 16 GB) | Q4_K - Medium | 40.2 tok/s | llamafile | ref |
| M1 (7-core GPU, 8 GB) | Q4_K - Medium | 38.5 tok/s | llamafile | ref |
| M1 (7-core GPU, 16 GB) | Q4_K - Medium | 37.9 tok/s | llamafile | ref |
| M2 (8-core GPU, 16 GB) | Q4_K - Medium | 35.3 tok/s | llamafile | ref |
| M2 (8-core GPU, 8 GB) | Q4_K - Medium | 34.5 tok/s | llamafile | ref |
Chips with published results for llama-3-2-1b-instruct
Data
benchmarks.json — full dataset · models.json — model summaries · benchmarks.csv — CSV export