Cheapest box to run Qwen3-32B at Q6_K
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 Q6_K needs 30GB.
Cheapest Config that fits: Mac mini, M5 Pro, 48GB. Fits, 15GB headroom. Est. 7.6 tok/s.
Best offer today: $2,499 at Apple — in stock, checked 44 minutes ago.
Price history: 46 days recorded.
Offers — Mac mini, M5 Pro, 48GB, 512GB
- Applelist pricein stockchecked 44 minutes ago$2,499
- Mac mini, M6, 16GB$1,099Won't fit−17GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−9GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−1GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−9GB headroom
- Mac mini, M5 Pro, 48GB$2,499Fits15GB headroomest. 7.6 tok/s
- Mac Studio, M5 Max, 36GB$2,499Tight3GB headroomest. 11.4 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits29GB headroomest. 7.6 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostTight1GB headroomest. 44.4 tok/s
- Fits29GB headroomest. 13.5 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits15GB headroomest. 15.2 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits29GB headroomest. 15.2 tok/s
- Fits91GB headroomest. 6.8 tok/s
- Fits59GB headroomest. 20.3 tok/s
- Fits90GB headroomest. 13.5 tok/s
- Fits91GB headroomest. 6.8 tok/s
- Fits90GB headroomest. 15.2 tok/s
- Fits59GB headroomest. 29.7 tok/s
- Fits218GB headroomest. 20.3 tok/s
- Fits218GB headroomest. 29.7 tok/s
- Fits474GB headroomest. 29.7 tok/s
| Config | Memory | Price | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | Won't fit | −17GB | — |
| Mac mini, M6 | 24GB | $1,299 | Won't fit | −9GB | — |
| Mac mini, M6 | 32GB | $1,499 | Won't fit | −1GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | Won't fit | −9GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | Fits | 15GB | 7.6 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | Tight | 3GB | 11.4 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | Fits | 29GB | 7.6 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | Tight | 1GB | 44.4 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | Fits | 29GB | 13.5 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | Fits | 15GB | 15.2 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | Fits | 29GB | 15.2 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | Fits | 91GB | 6.8 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | Fits | 59GB | 20.3 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | Fits | 90GB | 13.5 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | Fits | 91GB | 6.8 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | Fits | 90GB | 15.2 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | Fits | 59GB | 29.7 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | Fits | 218GB | 20.3 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | Fits | 218GB | 29.7 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | Fits | 474GB | 29.7 tok/s |
GeForce RTX 5090 is a card, not a computer: every price shown for it is the cheapest listing we found plus $1,000 for the minimum host machine.
memory = 32B × 0.820 B/param (6.56 bits) + 0.262 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (32B active × 0.820 B/param) = 26.2 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 M5 Pro 48GB runs
- Qwen3-Coder-NextQ3_K_M, est. 105 tok/s
- Llama-3.3-70BQ3_K_M, est. 5.8 tok/s
- Qwen3.5-35B-A3BQ8_0, est. 48.2 tok/s
- Qwen3-32BQ8_0, est. 5.9 tok/s
- Gemma-4-31BQ8_0, est. 6.1 tok/s
- Qwen3-30B-A3BQ8_0, est. 43.8 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 307GB/s, usable memory 44GB of 48GB.