Apple MacBook Pro 14-inch (Nov 2023, M3): which AI models can it run?
Estimated from the specifications below. Choose the memory size you have or plan to buy, then read the table for that size.
Specifications
- Brand
- Apple
- Year
- 2023
- Chip
- Apple M3
- Processor
- 8-core CPU (4 performance, 4 efficiency)
- Graphics
- 10-core GPU
- Memory type
- unified memory
- Memory options
- 8 GB, 16 GB, 24 GB
- Memory bandwidth
- 100 GB/s
Sources: https://support.apple.com/en-us/117735
Apple lists 100GB/s.
With 8 GB of memory
About 5.6 GB of it can hold a model.
| Model | Fit | Needs (GB) | Writing speed (tokens per second) | Speed | Quality | Basis |
|---|---|---|---|---|---|---|
| Llama 3.2 3B llama3.2:3b |
Fits | 5 | 18 to 32 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b |
Won't fit | 6 | not known | n/a | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Won't fit | 6.7 | not known | n/a | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Won't fit | 7.8 | not known | n/a | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Won't fit | 8.3 | not known | n/a | not measured yet | Estimated |
| Qwen3 8B qwen3:8b |
Won't fit | 8.9 | not known | n/a | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Won't fit | 15.9 | not known | n/a | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b |
Won't fit | 13.7 | not known | n/a | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Won't fit | 13.9 | not known | n/a | not measured yet | Estimated |
| Qwen3 14B qwen3:14b |
Won't fit | 13.4 | not known | n/a | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b |
Won't fit | 16.5 | not known | n/a | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b |
Won't fit | 27.2 | not known | n/a | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b |
Won't fit | 22.6 | not known | n/a | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b |
Won't fit | 26.3 | not known | n/a | not measured yet | Estimated |
| Llama 3.1 70B llama3.1:70b |
Won't fit | 51.5 | not known | n/a | not measured yet | Estimated |
| gpt-oss 120B gpt-oss:120b |
Won't fit | 70.5 | not known | n/a | not measured yet | Estimated |
With 16 GB of memory
About 11.2 GB of it can hold a model.
| Model | Fit | Needs (GB) | Writing speed (tokens per second) | Speed | Quality | Basis |
|---|---|---|---|---|---|---|
| Llama 3.2 3B llama3.2:3b |
Fits | 5 | 18 to 32 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 14 to 26 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 11 to 20 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 8 to 15 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 7.1 to 13 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 6.7 to 12 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Won't fit | 15.9 | not known | n/a | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b |
Won't fit | 13.7 | not known | n/a | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Won't fit | 13.9 | not known | n/a | not measured yet | Estimated |
| Qwen3 14B qwen3:14b |
Won't fit | 13.4 | not known | n/a | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b |
Won't fit | 16.5 | not known | n/a | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b |
Won't fit | 27.2 | not known | n/a | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b |
Won't fit | 22.6 | not known | n/a | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b |
Won't fit | 26.3 | not known | n/a | not measured yet | Estimated |
| Llama 3.1 70B llama3.1:70b |
Won't fit | 51.5 | not known | n/a | not measured yet | Estimated |
| gpt-oss 120B gpt-oss:120b |
Won't fit | 70.5 | not known | n/a | not measured yet | Estimated |
Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.
With 24 GB of memory
About 16.8 GB of it can hold a model.
| Model | Fit | Needs (GB) | Writing speed (tokens per second) | Speed | Quality | Basis |
|---|---|---|---|---|---|---|
| Llama 3.2 3B llama3.2:3b |
Fits | 5 | 18 to 32 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 14 to 26 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 11 to 20 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 8 to 15 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 7.1 to 13 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 6.7 to 12 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Tight | 15.9 | 4.3 to 8 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first |
Fits | 13.7 | 3.9 to 7.2 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Fits | 13.9 | 3.8 to 7.1 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| Qwen3 14B qwen3:14b · thinks first |
Fits | 13.4 | 3.8 to 7 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b · thinks first |
Tight | 16.5 | 8.7 to 16 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b |
Won't fit | 27.2 | not known | n/a | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b |
Won't fit | 22.6 | not known | n/a | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b |
Won't fit | 26.3 | not known | n/a | not measured yet | Estimated |
| Llama 3.1 70B llama3.1:70b |
Won't fit | 51.5 | not known | n/a | not measured yet | Estimated |
| gpt-oss 120B gpt-oss:120b |
Won't fit | 70.5 | not known | n/a | not measured yet | Estimated |
Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.
Speed is the speed of writing an answer, shown as a range. Reading speed is not estimated. How the estimates work · How close they are · Back to the finder