Cheapest box to run Qwen3-30B-A3B at Q4_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 Q4_K_M needs 20GB.
Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 9GB headroom. Est. 42.7 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−7GB headroom
- Mac mini, M6, 24GB$1,299Tight1GB headroomest. 42.7 tok/s
- Mac mini, M6, 32GB$1,499Fits9GB headroomest. 42.7 tok/s
- Mac mini, M5 Pro, 24GB$1,699Tight1GB headroomest. 77.0 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits24GB headroomest. 77.0 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits13GB headroomest. 154 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits38GB headroomest. 77.0 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits10GB headroomest. 450 tok/s
- Fits38GB headroomest. 137 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits24GB headroomest. 154 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits38GB headroomest. 154 tok/s
- Fits100GB headroomest. 68.5 tok/s
- Fits68GB headroomest. 206 tok/s
- Fits100GB headroomest. 137 tok/s
- Fits100GB headroomest. 68.5 tok/s
- Fits100GB headroomest. 154 tok/s
- Fits68GB headroomest. 301 tok/s
- Fits228GB headroomest. 206 tok/s
- Fits228GB headroomest. 301 tok/s
- Fits484GB headroomest. 301 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −7GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Tight | 1GB | 42.7 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 9GB | 42.7 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Tight | 1GB | 77.0 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 24GB | 77.0 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 13GB | 154 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 38GB | 77.0 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 10GB | 450 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 38GB | 137 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 24GB | 154 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 38GB | 154 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 100GB | 68.5 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 68GB | 206 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 100GB | 137 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 100GB | 68.5 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 100GB | 154 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 68GB | 301 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 228GB | 206 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 228GB | 301 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 484GB | 301 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 × 0.604 B/param (4.83 bits) + 0.098 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3.3B active × 0.604 B/param) = 2.0 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.