Cheapest box to run Qwen3-32B at Q3_K_M
Alibaba’s Qwen3-32B is 32B parameters, dense. The number below is computed from that and each vendor’s published specs, not asserted. Switch the quant or the context and it recomputes in place.
Qwen3-32B at Q3_K_M needs 19GB.
Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 10GB headroom. Est. 7.1 tok/s.
Best offer today: $1,499 at Apple — in stock, checked 9 hours ago.
Collecting price history — 1 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 32GB, 512GB
- Applelist pricein stockchecked 9 hours ago$1,499
- Mac mini, M6, 16GB$1,099Won't fit−6GB headroom
- Mac mini, M6, 24GB$1,299Tight2GB headroomest. 7.1 tok/s
- Mac mini, M6, 32GB$1,499Fits10GB headroomest. 7.1 tok/s
- Mac mini, M5 Pro, 24GB$1,699Tight2GB headroomest. 12.8 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits25GB headroomest. 12.8 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits14GB headroomest. 25.5 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits40GB headroomest. 12.8 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits25GB headroomest. 25.5 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits40GB headroomest. 25.5 tok/s
- Fits101GB headroomest. 11.3 tok/s
- Fits101GB headroomest. 25.5 tok/s
- Fits69GB headroomest. 49.9 tok/s
- GeForce RTX 5090, 32GB$5,699.99+hostFits12GB headroomest. 74.5 tok/s
- Fits229GB headroomest. 49.9 tok/s
- Fits485GB headroomest. 49.9 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −6GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Tight | 2GB | 7.1 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 10GB | 7.1 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Tight | 2GB | 12.8 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 25GB | 12.8 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 14GB | 25.5 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 40GB | 12.8 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 25GB | 25.5 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 40GB | 25.5 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 101GB | 11.3 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 101GB | 25.5 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 69GB | 49.9 tok/s |
| GeForce RTX 5090 | 32GB | $5,699.99+host | $178 | Fits | 12GB | 74.5 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 229GB | 49.9 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 485GB | 49.9 tok/s |
GeForce RTX 5090 is a card, not a computer: its price is the US street median plus $1,000 for the minimum host machine. NVIDIA's $1,999 MSRP is not a price anyone pays.
memory = 32B × 0.489 B/param (3.91 bits) + 0.262 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (32B active × 0.489 B/param) = 15.6 GB read per token
usable = memory − operating system reserve (8% on a Mac, 6% on a DGX Spark, 4% on a card)
Bandwidth is the vendor’s published figure. Every speed is an estimate and says so. Methodology.
What else Mac mini M6 32GB runs
- Qwen3-32BQ5_K_M, est. 4.9 tok/s
- Gemma-3-27BQ6_K, est. 5.0 tok/s
- gpt-oss-20bQ8_0, est. 22.2 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 170GB/s, usable memory 29GB of 32GB.