Cheapest box to run Qwen3-VL-8B-Instruct at Q3_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 Q3_K_M needs 6GB.
Cheapest Config that fits: Mac mini, M6, 16GB. Fits, 7GB headroom. Est. 28.3 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$1,099Fits7GB headroomest. 28.3 tok/s
- Mac mini, M6, 24GB$1,299Fits15GB headroomest. 28.3 tok/s
- Mac mini, M6, 32GB$1,499Fits23GB headroomest. 28.3 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits15GB headroomest. 51.0 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits38GB headroomest. 51.0 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits27GB headroomest. 102 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits53GB headroomest. 51.0 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits24GB headroomest. 298 tok/s
- Fits53GB headroomest. 90.8 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits38GB headroomest. 102 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits53GB headroomest. 102 tok/s
- Fits114GB headroomest. 45.4 tok/s
- Fits82GB headroomest. 136 tok/s
- Fits114GB headroomest. 90.8 tok/s
- Fits114GB headroomest. 45.4 tok/s
- Fits114GB headroomest. 102 tok/s
- Fits82GB headroomest. 199 tok/s
- Fits242GB headroomest. 136 tok/s
- Fits242GB headroomest. 199 tok/s
- Fits498GB headroomest. 199 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Fits | 7GB | 28.3 tok/s |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 15GB | 28.3 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 23GB | 28.3 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 15GB | 51.0 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 38GB | 51.0 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 27GB | 102 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 53GB | 51.0 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 24GB | 298 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 53GB | 90.8 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 38GB | 102 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 53GB | 102 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 114GB | 45.4 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 82GB | 136 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 114GB | 90.8 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 114GB | 45.4 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 114GB | 102 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 82GB | 199 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 242GB | 136 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 242GB | 199 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 498GB | 199 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 × 0.489 B/param (3.91 bits) + 0.147 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (8B active × 0.489 B/param) = 3.9 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.