Cheapest box to run Qwen3-VL-8B-Instruct at Q4_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 Q4_K_M needs 7GB.
Cheapest Config that fits: Mac mini, M6, 16GB. Fits, 6GB headroom. Est. 22.9 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$1,099Fits6GB headroomest. 22.9 tok/s
- Mac mini, M6, 24GB$1,299Fits14GB headroomest. 22.9 tok/s
- Mac mini, M6, 32GB$1,499Fits22GB headroomest. 22.9 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits14GB headroomest. 41.3 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits37GB headroomest. 41.3 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits26GB headroomest. 82.6 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits52GB headroomest. 41.3 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits24GB headroomest. 241 tok/s
- Fits52GB headroomest. 73.5 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits37GB headroomest. 82.6 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits52GB headroomest. 82.6 tok/s
- Fits113GB headroomest. 36.7 tok/s
- Fits81GB headroomest. 110 tok/s
- Fits113GB headroomest. 73.5 tok/s
- Fits113GB headroomest. 36.7 tok/s
- Fits113GB headroomest. 82.6 tok/s
- Fits81GB headroomest. 161 tok/s
- Fits241GB headroomest. 110 tok/s
- Fits241GB headroomest. 161 tok/s
- Fits497GB headroomest. 161 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Fits | 6GB | 22.9 tok/s |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 14GB | 22.9 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 22GB | 22.9 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 14GB | 41.3 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 37GB | 41.3 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 26GB | 82.6 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 52GB | 41.3 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 24GB | 241 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 52GB | 73.5 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 37GB | 82.6 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 52GB | 82.6 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 113GB | 36.7 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 81GB | 110 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 113GB | 73.5 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 113GB | 36.7 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 113GB | 82.6 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 81GB | 161 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 241GB | 110 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 241GB | 161 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 497GB | 161 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 × 0.604 B/param (4.83 bits) + 0.147 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (8B active × 0.604 B/param) = 4.8 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.