Cheapest box to run gpt-oss-20b at Q4_K_M
OpenAI’s gpt-oss-20b is 21B parameters, 3.6B of them read per token. 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.
gpt-oss-20b at Q4_K_M needs 14GB.
Cheapest Config that fits: Mac mini, M6, 24GB. Fits, 7GB headroom. Est. 39.1 tok/s.
Best offer today: $1,299 at Apple — in stock, checked 10 hours ago.
Collecting price history — 2 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 24GB, 512GB
- Applelist pricein stockchecked 10 hours ago$1,299
- Mac mini, M6, 16GB$1,099Won't fit−1GB headroom
- Mac mini, M6, 24GB$1,299Fits7GB headroomest. 39.1 tok/s
- Mac mini, M6, 32GB$1,499Fits15GB headroomest. 39.1 tok/s
- Mac mini, M5 Pro, 24GB$1,699Fits7GB headroomest. 70.6 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits30GB headroomest. 70.6 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits19GB headroomest. 141 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits45GB headroomest. 70.6 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits16GB headroomest. 412 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits30GB headroomest. 141 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits45GB headroomest. 141 tok/s
- Fits106GB headroomest. 62.8 tok/s
- Fits106GB headroomest. 62.8 tok/s
- Fits106GB headroomest. 141 tok/s
- Fits74GB headroomest. 276 tok/s
- Fits234GB headroomest. 276 tok/s
- Fits490GB headroomest. 276 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −1GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Fits | 7GB | 39.1 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 15GB | 39.1 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Fits | 7GB | 70.6 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 30GB | 70.6 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 19GB | 141 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 45GB | 70.6 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 16GB | 412 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 30GB | 141 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 45GB | 141 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 106GB | 62.8 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 106GB | 62.8 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 106GB | 141 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 74GB | 276 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 234GB | 276 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 490GB | 276 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 = 21B × 0.604 B/param (4.83 bits) + 0.049 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3.6B active × 0.604 B/param) = 2.2 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
- Qwen3-32BQ3_K_M, est. 7.1 tok/s
- Gemma-3-27BQ4_K_M, est. 6.8 tok/s
- gpt-oss-20bQ6_K, est. 28.8 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.