Written by Jakub Rusinowski · Last updated July 12, 2026
Up to 24 GB unified memory at 100 GB/s — same memory ceiling as M2 but on the 3nm process. Fits 7–8B models at Q4 comfortably. Common in the MacBook Air, iMac, and Mac mini.
| VRAM | 24 GB unified memory |
| Memory Bandwidth | 100 GB/s |
| TDP | 22 W |
| Architecture | ARM, 3nm TSMC |
| Release Year | 2023 |
| MSRP at Launch | $1,099 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | 6.4–13 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | Does not fit — needs ~44 GB of 18 GB usable |
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
All models below run comfortably in 24 GB unified memory with Q4_K_M quantization.
| Llama 3.1 Family | Llama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| Llama 3.2 Family | Llama 3.2 11B Vision Instruct · 7 GB VRAM · Q4_K_M · llama-3-2 |
| Qwen 2.5 Family | Qwen 2.5 Coder 32B · 20 GB VRAM · Q4_K_M · ollama run qwen2.5-coder:32b |
| Gemma 3 | Gemma 3 27B Instruct · 17 GB VRAM · Q4_K_M · ollama run gemma3:27b |
| Phi-4 Mini | Phi-4 Mini (3.8B) · 3 GB VRAM · Q4_K_M · ollama run phi4-mini |
| Mistral Family | Mistral Small 3 (24B) · 15 GB VRAM · Q4_K_M · ollama run mistral-small |
| SmolLM2 | SmolLM2 1.7B Instruct · 2 GB VRAM · Q4_K_M · ollama run smollm2:1.7b |
| Qwen3.8 | Qwen3.8 27B · 18 GB VRAM · Q4_K_M · ollama run qwen3.8:27b |
Install Ollama then run the recommended model for this GPU:
ollama run llama3.2:3b
Yes — the Apple M3 has 24 GB unified memory and runs Up to 24 GB unified memory at 100 GB/s — same memory ceiling as M2 but on the 3nm process. Fits 7–8B models at Q4 comfor
The Apple M3 is estimated to run Llama 3.1 8B at 6.4–13 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 18 GB usable. These are modelled estimates, not measurements — see /en/methodology.
With 24 GB you can run: Llama 3.1 Family, Llama 3.2 Family, Qwen 2.5 Family, Gemma 3, Phi-4 Mini. Use Ollama for the easiest setup: ollama run llama3.2:3b.
← All GPU Reviews | All Hardware | Check Your Hardware | Full Benchmarks | Can I Run It?