Mac mini, M6, 32GB
512GB of storage, 170GB/s of memory bandwidth, and 29GB of unified memory left for a model once macOS has taken its share. It holds 14 of the 30 models we track.
Offers
checked 45 days ago- Applelist pricecheapest todayin stockchecked 45 days ago$1,499
- Expercomnot availablechecked 45 days ago$1,499
Sold out.
- B&H Photonot availablechecked 45 days ago$1,599
Preorder, ships about 22 Sep.
2 reseller listings, from $1,499 at Expercom to $1,599 at B&H Photo — the same 32GB either way. No reseller undercuts Apple on this Config, so Apple direct is the price to beat.
Timing
Collecting price history — 0 of 90 days. No timing verdict yet.
Models it runs — 8K context
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Won't fit— headroom
- Qwen3.5-35B-A3BQ5_K_MTight3GB headroomest. 40.0 tok/s
- Qwen3-32BQ5_K_MTight3GB headroomest. 4.9 tok/s
- Gemma-4-31BQ6_KTight1GB headroomest. 4.4 tok/s
- Qwen3-30B-A3BQ6_KTight2GB headroomest. 31.4 tok/s
- Gemma-3-27BQ6_KTight4GB headroomest. 5.0 tok/s
- Qwen3.6-27BQ6_KFits5GB headroomest. 5.0 tok/s
- Gemma-4-26B-A4BQ8_0Tight1GB headroomest. 21.1 tok/s
- Tight1GB headroomest. 4.3 tok/s
- gpt-oss-20bQ8_0Fits5GB headroomest. 22.2 tok/s
- Phi-4Q8_0Fits11GB headroomest. 7.4 tok/s
- Gemma-4-12BBF16Tight3GB headroomest. 4.6 tok/s
- Fits11GB headroomest. 6.9 tok/s
- Gemma-3n-E4BBF16Fits14GB headroomest. 13.8 tok/s
- Qwen3-4BBF16Fits19GB headroomest. 13.8 tok/s
| Model | Best quant | Fit | Headroom | Est. speed |
|---|---|---|---|---|
| Llama-4-Behemoth | — | Won't fit | — | — |
| DeepSeek-V4-Pro | — | Won't fit | — | — |
| Kimi-K2-Instruct | — | Won't fit | — | — |
| DeepSeek-V3 | — | Won't fit | — | — |
| DeepSeek-R1 | — | Won't fit | — | — |
| Qwen3-Coder-480B-A35B-Instruct | — | Won't fit | — | — |
| Llama-4-Maverick-17B-128E | — | Won't fit | — | — |
| GLM-4.6 | — | Won't fit | — | — |
| DeepSeek-V4-Flash | — | Won't fit | — | — |
| Qwen3-235B-A22B | — | Won't fit | — | — |
| MiniMax-M2 | — | Won't fit | — | — |
| Mistral-Large-2411 | — | Won't fit | — | — |
| gpt-oss-120b | — | Won't fit | — | — |
| Llama-4-Scout-17B-16E | — | Won't fit | — | — |
| Qwen3-Coder-Next | — | Won't fit | — | — |
| Llama-3.3-70B | — | Won't fit | — | — |
| Qwen3.5-35B-A3B | Q5_K_M | Tight | 3GB | 40.0 tok/s |
| Qwen3-32B | Q5_K_M | Tight | 3GB | 4.9 tok/s |
| Gemma-4-31B | Q6_K | Tight | 1GB | 4.4 tok/s |
| Qwen3-30B-A3B | Q6_K | Tight | 2GB | 31.4 tok/s |
| Gemma-3-27B | Q6_K | Tight | 4GB | 5.0 tok/s |
| Qwen3.6-27B | Q6_K | Fits | 5GB | 5.0 tok/s |
| Gemma-4-26B-A4B | Q8_0 | Tight | 1GB | 21.1 tok/s |
| Devstral-Small-2507 | Q8_0 | Tight | 1GB | 4.3 tok/s |
| gpt-oss-20b | Q8_0 | Fits | 5GB | 22.2 tok/s |
| Phi-4 | Q8_0 | Fits | 11GB | 7.4 tok/s |
| Gemma-4-12B | BF16 | Tight | 3GB | 4.6 tok/s |
| Qwen3-VL-8B-Instruct | BF16 | Fits | 11GB | 6.9 tok/s |
| Gemma-3n-E4B | BF16 | Fits | 14GB | 13.8 tok/s |
| Qwen3-4B | BF16 | Fits | 19GB | 13.8 tok/s |
Best quant is the highest-quality one that still loads with headroom. Every speed is an estimate; the formula is here.