Cheapest box to run Qwen3-30B-A3B at Q5_K_M
Alibaba’s Qwen3-30B-A3B is 30.5B parameters, 3.3B of them read per token. 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.
Qwen3-30B-A3B at Q5_K_M needs 24GB.
Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 5GB headroom. Est. 36.3 tok/s.
Best offer today: $1,499 at Apple — in stock, checked 57 minutes ago.
Collecting price history — 3 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 32GB, 512GB
- Mac mini, M6, 16GB$1,099Won't fit−11GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−3GB headroom
- Mac mini, M6, 32GB$1,499Fits5GB headroomest. 36.3 tok/s
- Mac mini, M5 Pro, 24GB$1,699Won't fit−3GB headroom
- Mac mini, M5 Pro, 48GB$2,499Fits21GB headroomest. 65.6 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits9GB headroomest. 131 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits35GB headroomest. 65.6 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits7GB headroomest. 383 tok/s
- Fits35GB headroomest. 117 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits21GB headroomest. 131 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits35GB headroomest. 131 tok/s
- Fits97GB headroomest. 58.4 tok/s
- Fits65GB headroomest. 175 tok/s
- Fits96GB headroomest. 117 tok/s
- Fits97GB headroomest. 58.4 tok/s
- Fits96GB headroomest. 131 tok/s
- Fits65GB headroomest. 257 tok/s
- Fits224GB headroomest. 175 tok/s
- Fits224GB headroomest. 257 tok/s
- Fits480GB headroomest. 257 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −11GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −3GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 5GB | 36.3 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −3GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 21GB | 65.6 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 9GB | 131 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 35GB | 65.6 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 7GB | 383 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 35GB | 117 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 21GB | 131 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 35GB | 131 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 97GB | 58.4 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 65GB | 175 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 96GB | 117 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 97GB | 58.4 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 96GB | 131 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 65GB | 257 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 224GB | 175 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 224GB | 257 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 480GB | 257 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 = 30.5B × 0.709 B/param (5.67 bits) + 0.098 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3.3B active × 0.709 B/param) = 2.3 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
- Qwen3-30B-A3BQ6_K, est. 31.4 tok/s
- Gemma-3-27BQ6_K, est. 5.0 tok/s
- Devstral-Small-2507Q8_0, est. 4.3 tok/s
- gpt-oss-20bQ8_0, est. 22.2 tok/s
- Phi-4Q8_0, est. 7.4 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.