Every memory option compared, 200 GB/s memory bandwidth. Updated 2 November 2026.
M1 Pro / M2 Pro are sold with 16, 32 GB of memory. Counting the 31 models tracked here: 16 GB runs 16 models well; 32 GB runs 23 models well. Memory bandwidth is 200 GB/s, about 1.7 times the memory speed of a base M4 (120 GB/s), so the same model generates words proportionally faster. Apple Silicon shares one pool of memory between the processor and the GPU, and macOS lets the GPU use about two thirds of it on Macs up to 36 GB and about three quarters above that, so the memory you buy decides which models load at all.
| Model | 16 GB | 32 GB |
|---|---|---|
| Wan 2.2 14B | No | Slow about 53 min |
| LTX-2.3 | No | Good about 4 min |
| Qwen 3.6 35B A3B | No | Tight 27/s |
| Qwen 3.5 35B A3B | No | Tight 29/s |
| Gemma 4 31B | No | Slow 5/s |
| DeepSeek R1 32B | No | Slow 5/s |
| Qwen3 Coder 30B | No | Great 29/s |
| Qwen 3.6 27B | No | Slow 6/s |
| Gemma 4 26B A4B | No | Great 23/s |
| Z-Image Turbo 6B | Slow about 2 min | Good about 49 s |
| Wan 2.2 5B | Slow about 27 min | Good about 13 min |
| gpt-oss 20B | Tight 22/s | Great 24/s |
| ACE-Step 1.5 | Good about 3 min | Good about 3 min |
| FLUX.2 klein 4B | Good about 34 s | Good about 34 s |
| Phi-4 14B | Great 11/s | Great 11/s |
| Gemma 4 12B | Great 14/s | Great 14/s |
| Stable Diffusion XL | Good about 18 s | Good about 18 s |
| Qwen3 TTS 1.7B | Good about 52 s | Good about 52 s |
| Gemma 4 E4B | Great 33/s | Great 33/s |
| Qwen 3.5 9B | Great 16/s | Great 16/s |
| Qwen3 VL 8B | Great 17/s | Great 17/s |
| DeepSeek R1 8B | Great 20/s | Great 20/s |
| Qwen2.5 Coder 7B | Great 23/s | Great 23/s |
| Gemma 4 E2B | Great 53/s | Great 53/s |
| Whisper large-v3 turbo | Good about 1 min | Good about 1 min |
| Qwen 3.5 4B | Great 32/s | Great 32/s |
| Kokoro TTS | Good about 11 s | Good about 11 s |
Text models show words a second. Image, video and voice models show the time per job (image, 4 second clip, minute of speech or similar).
As an Amazon Associate I earn from qualifying purchases.
About 15 GB is usable by the GPU. The largest chat or coding model that fits is gpt-oss 20B (15.2 GB), generating about 22 words a second with no spare room. The quickest is Gemma 4 E2B at about 53 words a second. Closest miss: Gemma 4 26B A4B, which needs about 19.4 GB (4 GB more than this configuration can give the GPU).
Find M2 Pro Macs with 16 GB on Amazon
About 30 GB is usable by the GPU. The largest chat or coding model that fits is Qwen 3.6 35B A3B (24.6 GB), generating about 27 words a second with 5.8 GB to spare. The quickest is Gemma 4 E2B at about 53 words a second. Closest miss: Llama 3.3 70B, which needs about 45.6 GB (15 GB more than this configuration can give the GPU).
For everyday chat, 16 GB runs 16 of 31 models well. 16 GB to 32 GB unlocks 7 more: Gemma 4 26B A4B, Qwen 3.5 35B A3B, Qwen3 Coder 30B, Qwen 3.6 35B A3B, Z-Image Turbo 6B and more.
No. It needs about 21.5 GB of usable memory and this chip's largest option is 32 GB.
16 GB runs gpt-oss 20B at about 22 words a second; 32 GB runs gpt-oss 20B at about 24 words a second.
As an Amazon Associate I earn from qualifying purchases.
Unlocks 4 more: Gemma 4 31B, Qwen 3.6 27B, DeepSeek R1 32B, Wan 2.2 14B.
Unlocks 7 more: Gemma 4 31B, Llama 3.3 70B, Qwen 3.5 122B A10B, gpt-oss 120B and more.