Cheapest box to run Qwen3-VL-8B-Instruct at Q5_K_M
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 Q5_K_M needs 8GB.
Cheapest Config that fits: Mac mini, M6, 16GB. Fits, 5GB headroom. Est. 19.5 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$1,099Fits5GB headroomest. 19.5 tok/s
- Mac mini, M6, 24GB$1,299Fits13GB headroomest. 19.5 tok/s
- Mac mini, M6, 32GB$1,499Fits21GB headroomest. 19.5 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits13GB headroomest. 35.2 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits36GB headroomest. 35.2 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits25GB headroomest. 70.4 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits51GB headroomest. 35.2 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits23GB headroomest. 205 tok/s
- Fits51GB headroomest. 62.6 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits36GB headroomest. 70.4 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits51GB headroomest. 70.4 tok/s
- Fits112GB headroomest. 31.3 tok/s
- Fits80GB headroomest. 93.9 tok/s
- Fits112GB headroomest. 62.6 tok/s
- Fits112GB headroomest. 31.3 tok/s
- Fits112GB headroomest. 70.4 tok/s
- Fits80GB headroomest. 138 tok/s
- Fits240GB headroomest. 93.9 tok/s
- Fits240GB headroomest. 138 tok/s
- Fits496GB headroomest. 138 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Fits | 5GB | 19.5 tok/s |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 13GB | 19.5 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 21GB | 19.5 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 13GB | 35.2 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 36GB | 35.2 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 25GB | 70.4 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 51GB | 35.2 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 23GB | 205 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 51GB | 62.6 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 36GB | 70.4 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 51GB | 70.4 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 112GB | 31.3 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 80GB | 93.9 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 112GB | 62.6 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 112GB | 31.3 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 112GB | 70.4 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 80GB | 138 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 240GB | 93.9 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 240GB | 138 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 496GB | 138 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 × 0.709 B/param (5.67 bits) + 0.147 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (8B active × 0.709 B/param) = 5.7 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.