Cheapest box to run Qwen3.6-27B at Q3_K_M
Alibaba’s Qwen3.6-27B is 27B 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.
Qwen3.6-27B at Q3_K_M needs 15GB.
Cheapest Config that fits: Mac mini, M6, 24GB. Fits, 6GB headroom. Est. 8.4 tok/s.
Best offer today: $1,299 at Best Buy — in stock, checked 33 days ago.
Price history: 34 days recorded.
Same hybrid family: 16 of 64 layers are full attention; the rest cache nothing per token.
Offers — Mac mini, M6, 24GB, 512GB
- Mac mini, M6, 16GB$1,099Won't fit−2GB headroom
- Mac mini, M6, 24GB$1,299Fits6GB headroomest. 8.4 tok/s
- Mac mini, M6, 32GB$1,499Fits14GB headroomest. 8.4 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits6GB headroomest. 15.1 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits29GB headroomest. 15.1 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits18GB headroomest. 22.7 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits44GB headroomest. 15.1 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits16GB headroomest. 88.3 tok/s
- Fits44GB headroomest. 26.9 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits29GB headroomest. 30.2 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits44GB headroomest. 30.2 tok/s
- Fits105GB headroomest. 13.4 tok/s
- Fits73GB headroomest. 40.3 tok/s
- Fits105GB headroomest. 26.9 tok/s
- Fits105GB headroomest. 13.4 tok/s
- Fits105GB headroomest. 30.2 tok/s
- Fits73GB headroomest. 59.1 tok/s
- Fits233GB headroomest. 40.3 tok/s
- Fits233GB headroomest. 59.1 tok/s
- Fits489GB headroomest. 59.1 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −2GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 6GB | 8.4 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 14GB | 8.4 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 6GB | 15.1 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 29GB | 15.1 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 18GB | 22.7 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 44GB | 15.1 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 16GB | 88.3 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 44GB | 26.9 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 29GB | 30.2 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 44GB | 30.2 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 105GB | 13.4 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 73GB | 40.3 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 105GB | 26.9 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 105GB | 13.4 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 105GB | 30.2 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 73GB | 59.1 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 233GB | 40.3 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 233GB | 59.1 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 489GB | 59.1 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 = 27B × 0.489 B/param (3.91 bits) + 0.067 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (27B active × 0.489 B/param) = 13.2 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 M6 24GB runs
- Qwen3.5-35B-A3BQ3_K_M, est. 58.0 tok/s
- Qwen3-32BQ3_K_M, est. 7.1 tok/s
- Gemma-4-31BQ3_K_M, est. 7.4 tok/s
- Qwen3-30B-A3BQ4_K_M, est. 42.7 tok/s
- Gemma-3-27BQ4_K_M, est. 6.8 tok/s
- Qwen3.6-27BQ5_K_M, est. 5.8 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 170GB/s, usable memory 21GB of 24GB.