Apple · M5 Pro · 64 GB · Qwen3.8 27B · Q4_K_M: ~11 tok/s
Apple Mac mini M5 Pro, 64 GB
The cheapest way into 64 GB of unified memory: enough for a 30B-class model at Q8 or a 70B at a small quant, in a box the size of a sandwich. Bandwidth is a quarter of an M5 Ultra's, so big dense models are slow.
Lowest price right now
$3,757.78
eBay · $3,750 + $7.78 shipping · $58 per GB · observed 2026-10-18 02:55 UTC
Buy the cheapest on eBay, $3,757.78
$3,750 + $7.78 shipping · New · stevola 912 · 96.3%
Price alert
One email per move, item plus shipping. Clear the price to hear about any drop. Manage alerts.
Price history
Tracking started today. The chart appears once there is a second day of data.
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$3,757.78 $3,750 + $7.78 shipping |
new and used | 2026-10-18 02:55 UTC | Go to eBay |
On eBay now
1 listings passed our filters at the last check. Cheapest delivered first. Seller reputation is feedback count and positive rate.
-
$3,757.78$3,750 + $7.78 shipping
What it runs
For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user, at 8K and at 32K of context. On a card, a model too big for its memory can still run with part of the weights in system RAM; we assume 64 GB, and the speed shown accounts for it. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.
| Model | Quant | Needs at 8K | Fit | Max context | Decode at 8K | At 32K | Prefill tok/s |
|---|---|---|---|---|---|---|---|
| DeepSeek | |||||||
| DeepSeek V4.1 Flash 552B-A16B Sep 2026 | Q4_K_M | 338 GB | does not fit | ||||
| DeepSeek V4 Flash 284B-A13B Jul 2026 | Q4_K_M | 175 GB | does not fit | ||||
| DeepSeek V3.1 671B-A37B Aug 2025 | Q4_K_M | 411 GB | does not fit | ||||
| Gemma | |||||||
| Gemma 4 12B May 2026 | Q8_0 | 14 GB | fits | 128K+ | ~14 | ~14 | ~370 |
| Gemma 4 31B Mar 2026 | Q8_0 | 35 GB | fits | 128K+ | ~5.5 | ~5.2 | ~140 |
| Gemma 4 26B-A4B Mar 2026 | Q8_0 | 28 GB | fits | 128K+ | ~38 | ~34 | ~1,200 |
| Gemma 3 27B Mar 2025 | Q8_0 | 31 GB | fits | 128K+ | ~6.2 | ~5.8 | ~160 |
| GLM | |||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | ||||
| GLM-5.3 Flash 320B-A18B Aug 2026 | Q4_K_M | 197 GB | does not fit | ||||
| GLM-4.6 355B-A32B Sep 2025 | Q4_K_M | 221 GB | does not fit | ||||
| GLM-4.5 Air 106B-A12B Jul 2025 | Q3_K_M | 55 GB | fits | 54K | ~23 | ~15 | ~360 |
| gpt-oss | |||||||
| gpt-oss-120b Aug 2025 | Q3_K_M | 59 GB | fits | 69K | ~49 | ~33 | ~860 |
| gpt-oss-20b Aug 2025 | Q8_0 | 24 GB | fits | 128K+ | ~38 | ~30 | ~1,200 |
| Llama | |||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q3_K_M | 57 GB | fits | 45K | ~17 | ~12 | ~260 |
| Llama 3.3 70B Dec 2024 | Q6_K | 62 GB | fits | 13K | ~3.0 | ~62 | |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 128K+ | ~19 | ~14 | ~550 |
| MiMo | |||||||
| MiMo V2.6 Pro 1.02T-A42B Sep 2026 | Q4_K_M | 624 GB | does not fit | ||||
| MiMo V2.6 Flash 309B-A15B Sep 2026 | Q4_K_M | 190 GB | does not fit | ||||
| Mistral | |||||||
| Mistral Medium 3.5 128B Mar 2026 | IQ2_M | 48 GB | fits | 51K | ~4.0 | ~3.3 | ~34 |
| Mistral Small 4 119B-A6.5B Mar 2026 | IQ2_M | 47 GB | fits | 36K | ~24 | ~8.3 | ~670 |
| Mistral Small 3.2 24B Jun 2025 | Q8_0 | 28 GB | fits | 128K+ | ~6.9 | ~6.0 | ~180 |
| Nemotron | |||||||
| Nemotron 3.5 Lightning 30B-A3B Aug 2026 | Q8_0 | 35 GB | fits | 128K+ | ~42 | ~40 | ~1,300 |
| Qwen | |||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q3_K_M | 63 GB | fits | 49K | ~49 | ~42 | ~730 |
| Qwen3.8 27B Aug 2026 (your pick) | Q8_0 | 31 GB | fits | 128K+ | ~6.3 | ~6.0 | ~160 |
| Qwen3.6 27B Apr 2026 | Q8_0 | 31 GB | fits | 128K+ | ~6.3 | ~6.0 | ~160 |
| Qwen3.6 35B-A3B Apr 2026 | Q8_0 | 39 GB | fits | 128K+ | ~46 | ~41 | ~1,500 |
| Qwen3.5 9B Feb 2026 | Q8_0 | 11 GB | fits | 128K+ | ~19 | ~17 | ~490 |
| Qwen3 Coder 480B-A35B Jul 2025 | Q4_K_M | 296 GB | does not fit | ||||
| Qwen3 235B-A22B Jul 2025 | Q4_K_M | 146 GB | does not fit | ||||
| Qwen3 32B Apr 2025 | Q8_0 | 38 GB | fits | 103K | ~5.0 | ~4.2 | ~130 |
Specifications
- Memory
- 64 GB LPDDR5x unified
- Memory bandwidth
- 307 GB/s
- Bus width
- 256-bit
- FP16 (dense)
- 35 TFLOPS
- Form factor
- Mini PC, 127 x 127 x 50 mm
- CPU
- 15-core CPU, 16-core GPU with neural accelerators (18-core CPU, 20-core GPU optional), 16-core Neural Engine
- Architecture
- M5 Pro
- Launched
- 2026
- MSRP
- $2,699
Source: manufacturer specifications.