Cheapest box to run Qwen3-VL-8B-Instruct at Q6_K
Alibaba’s Qwen3-VL-8B-Instruct is 8B 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-VL-8B-Instruct at Q6_K needs 9GB.
Cheapest Config that fits: Mac mini, M6, 16GB. Fits, 4GB headroom. Est. 16.8 tok/s.
Best offer today: $1,099 at Apple — in stock, checked 42 hours ago.
Collecting price history — 3 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 16GB, 512GB
- Applelist pricein stockchecked 42 hours ago$1,099
- Mac mini, M6, 16GB$1,099Fits4GB headroomest. 16.8 tok/s
- Mac mini, M6, 24GB$1,299Fits12GB headroomest. 16.8 tok/s
- Mac mini, M6, 32GB$1,499Fits20GB headroomest. 16.8 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits12GB headroomest. 30.4 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits35GB headroomest. 30.4 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits24GB headroomest. 60.8 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits50GB headroomest. 30.4 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits22GB headroomest. 178 tok/s
- Fits50GB headroomest. 54.1 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits35GB headroomest. 60.8 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits50GB headroomest. 60.8 tok/s
- Fits111GB headroomest. 27.1 tok/s
- Fits79GB headroomest. 81.2 tok/s
- Fits111GB headroomest. 54.1 tok/s
- Fits111GB headroomest. 27.1 tok/s
- Fits111GB headroomest. 60.8 tok/s
- Fits79GB headroomest. 119 tok/s
- Fits239GB headroomest. 81.2 tok/s
- Fits239GB headroomest. 119 tok/s
- Fits495GB headroomest. 119 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Fits | 4GB | 16.8 tok/s |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 12GB | 16.8 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 20GB | 16.8 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 12GB | 30.4 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 35GB | 30.4 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 24GB | 60.8 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 50GB | 30.4 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 22GB | 178 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 50GB | 54.1 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 35GB | 60.8 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 50GB | 60.8 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 111GB | 27.1 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 79GB | 81.2 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 111GB | 54.1 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 111GB | 27.1 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 111GB | 60.8 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 79GB | 119 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 239GB | 81.2 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 239GB | 119 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 495GB | 119 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 = 8B × 0.820 B/param (6.56 bits) + 0.147 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (8B active × 0.820 B/param) = 6.6 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.