Cheapest box to run Qwen3-4B at Q4_K_M
Alibaba’s Qwen3-4B is 4B 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.
Qwen3-4B at Q4_K_M needs 5GB.
Cheapest Config that fits: Mac mini, M6, 16GB. Fits, 8GB headroom. Est. 45.8 tok/s.
Best offer today: $1,099 at Apple — in stock, checked 40 hours ago.
Collecting price history — 3 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 16GB, 512GB
- Applelist pricein stockchecked 40 hours ago$1,099
- Mac mini, M6, 16GB$1,099Fits8GB headroomest. 45.8 tok/s
- Mac mini, M6, 24GB$1,299Fits16GB headroomest. 45.8 tok/s
- Mac mini, M6, 32GB$1,499Fits24GB headroomest. 45.8 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits16GB headroomest. 82.6 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits39GB headroomest. 82.6 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits28GB headroomest. 165 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits54GB headroomest. 82.6 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits26GB headroomest. 482 tok/s
- Fits54GB headroomest. 147 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits39GB headroomest. 165 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits54GB headroomest. 165 tok/s
- Fits116GB headroomest. 73.5 tok/s
- Fits84GB headroomest. 220 tok/s
- Fits115GB headroomest. 147 tok/s
- Fits116GB headroomest. 73.5 tok/s
- Fits115GB headroomest. 165 tok/s
- Fits84GB headroomest. 323 tok/s
- Fits243GB headroomest. 220 tok/s
- Fits243GB headroomest. 323 tok/s
- Fits499GB headroomest. 323 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Fits | 8GB | 45.8 tok/s |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 16GB | 45.8 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 24GB | 45.8 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 16GB | 82.6 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 39GB | 82.6 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 28GB | 165 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 54GB | 82.6 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 26GB | 482 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 54GB | 147 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 39GB | 165 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 54GB | 165 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 116GB | 73.5 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 84GB | 220 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 115GB | 147 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 116GB | 73.5 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 115GB | 165 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 84GB | 323 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 243GB | 220 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 243GB | 323 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 499GB | 323 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 = 4B × 0.604 B/param (4.83 bits) + 0.147 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (4B active × 0.604 B/param) = 2.4 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 16GB runs
- gpt-oss-20bQ3_K_M, est. 48.3 tok/s
- Phi-4Q5_K_M, est. 11.1 tok/s
- Qwen3-VL-8B-InstructQ8_0, est. 13.0 tok/s
- Gemma-3n-E4BQ8_0, est. 26.0 tok/s
- Qwen3-4BBF16, est. 13.8 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 170GB/s, usable memory 13GB of 16GB.