Every memory option compared, 68 GB/s memory bandwidth. Updated 2 November 2026.
M1 is sold with 8, 16 GB of memory. Counting the 31 models tracked here: 8 GB runs 7 models well; 16 GB runs 12 models well. Memory bandwidth is 68 GB/s, only about 57% of the memory speed of a base M4 (120 GB/s), so expect the same model to be slower. 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 | 8 GB | 16 GB |
|---|---|---|
| Z-Image Turbo 6B | No | Slow about 3 min |
| Wan 2.2 5B | No | Slow about 50 min |
| gpt-oss 20B | No | Tight 8/s |
| ACE-Step 1.5 | No | Good about 5 min |
| FLUX.2 klein 4B | No | Good about 1 min |
| Phi-4 14B | No | Slow 4/s |
| Gemma 4 12B | No | Slow 5/s |
| Stable Diffusion XL | Slow about 1 min | Good about 30 s |
| Qwen3 TTS 1.7B | Slow about 3 min | Good about 2 min |
| Gemma 4 E4B | Tight 10/s | Good 11/s |
| Qwen 3.5 9B | Slow 5/s | Slow 5/s |
| Qwen3 VL 8B | Slow 5/s | Slow 6/s |
| DeepSeek R1 8B | Tight 6/s | Good 7/s |
| Qwen2.5 Coder 7B | Tight 7/s | Good 8/s |
| Gemma 4 E2B | Great 18/s | Great 18/s |
| Whisper large-v3 turbo | Good about 2 min | Good about 2 min |
| Qwen 3.5 4B | Good 11/s | Good 11/s |
| Kokoro TTS | Good about 20 s | Good about 20 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 8 GB is usable by the GPU. The largest chat or coding model that fits is Gemma 4 E4B (7.4 GB), generating about 10 words a second with 0.2 GB to spare. The quickest is Gemma 4 E2B at about 18 words a second. Closest miss: Gemma 4 12B, which needs about 8.9 GB (1 GB more than this configuration can give the GPU).
Find M1 Macs with 8 GB on Amazon
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 8 words a second with no spare room. The quickest is Gemma 4 E2B at about 18 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).
For everyday chat, 8 GB runs 7 of 31 models well. 8 GB to 16 GB unlocks 5 more: gpt-oss 20B, Stable Diffusion XL, FLUX.2 klein 4B, Qwen3 TTS 1.7B, ACE-Step 1.5.
No. It needs about 21.5 GB of usable memory and this chip's largest option is 16 GB.
8 GB cannot run gpt-oss 20B; 16 GB runs gpt-oss 20B at about 8 words a second.
As an Amazon Associate I earn from qualifying purchases.
Unlocks 15 more: Qwen 3.5 9B, Gemma 4 12B, Gemma 4 26B A4B, Qwen 3.5 35B A3B and more.
Unlocks 18 more: Qwen 3.5 9B, Gemma 4 12B, Gemma 4 26B A4B, Qwen 3.5 35B A3B and more.