Mac mini, M5 Pro, 24GB
512GB of storage, 307GB/s of memory bandwidth, and 21GB of unified memory left for a model once macOS has taken its share. It holds 14 of the 30 models we track.
Offers
checked 2 hours ago- Expercomnot availablechecked 43 minutes ago$859
Sold out.
- Applelist pricecheapest todayin stockchecked 2 hours ago$1,699
Expercom undercuts Apple by $840.
Timing
Wait. It has been $859 in the last 46 days, $840 below today.
- 27 Aug 2026$1,699
- 29 Aug 2026$1,519
- 8 Sept 2026$1,429
- 8 Sept 2026$949
- 10 Sept 2026$899
- 6 Oct 2026$859
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-A3BQ3_K_MTight3GB headroomest. 105 tok/s
- Qwen3-32BQ3_K_MTight2GB headroomest. 12.8 tok/s
- Gemma-4-31BQ3_K_MTight3GB headroomest. 13.3 tok/s
- Qwen3-30B-A3BQ4_K_MTight1GB headroomest. 77.0 tok/s
- Gemma-3-27BQ4_K_MTight1GB headroomest. 12.2 tok/s
- Qwen3.6-27BQ5_K_MTight0GB headroomest. 10.4 tok/s
- Gemma-4-26B-A4BQ5_K_MTight2GB headroomest. 57.0 tok/s
- Devstral-Small-2507Q5_K_MTight1GB headroomest. 11.7 tok/s
- gpt-oss-20bQ6_KTight2GB headroomest. 52.0 tok/s
- Phi-4Q8_0Tight3GB headroomest. 13.4 tok/s
- Gemma-4-12BQ8_0Fits7GB headroomest. 15.7 tok/s
- Tight3GB headroomest. 12.5 tok/s
- Gemma-3n-E4BBF16Fits6GB headroomest. 24.9 tok/s
- Qwen3-4BBF16Fits11GB headroomest. 24.9 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 | Q3_K_M | Tight | 3GB | 105 tok/s |
| Qwen3-32B | Q3_K_M | Tight | 2GB | 12.8 tok/s |
| Gemma-4-31B | Q3_K_M | Tight | 3GB | 13.3 tok/s |
| Qwen3-30B-A3B | Q4_K_M | Tight | 1GB | 77.0 tok/s |
| Gemma-3-27B | Q4_K_M | Tight | 1GB | 12.2 tok/s |
| Qwen3.6-27B | Q5_K_M | Tight | 0GB | 10.4 tok/s |
| Gemma-4-26B-A4B | Q5_K_M | Tight | 2GB | 57.0 tok/s |
| Devstral-Small-2507 | Q5_K_M | Tight | 1GB | 11.7 tok/s |
| gpt-oss-20b | Q6_K | Tight | 2GB | 52.0 tok/s |
| Phi-4 | Q8_0 | Tight | 3GB | 13.4 tok/s |
| Gemma-4-12B | Q8_0 | Fits | 7GB | 15.7 tok/s |
| Qwen3-VL-8B-Instruct | BF16 | Tight | 3GB | 12.5 tok/s |
| Gemma-3n-E4B | BF16 | Fits | 6GB | 24.9 tok/s |
| Qwen3-4B | BF16 | Fits | 11GB | 24.9 tok/s |
Best quant is the highest-quality one that still loads with headroom. Every speed is an estimate; the formula is here.