How much memory does gpt-oss-20b at Q5_K_M need?

16GB. That is 15GB of weights at 5.67 bits per weight, 0.4GB of K/V cache at 8K context, and 1.2GB of runtime overhead.

Which machine is cheapest for gpt-oss-20b at Q5_K_M?

Mac mini, M6, 24GB, $1,299 at Apple. It fits with 5GB of headroom and decodes at an est. 33.3 tok/s.

Cheapest box to run gpt-oss-20b at Q5_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.

Fit finderprices checked 19 minutes ago

Quant

Context

gpt-oss-20b at Q5_K_M needs 16GB.

Cheapest Config that fits: Mac mini, M6, 24GB. Fits, 5GB headroom. Est. 33.3 tok/s.

Best offer today: $1,299 at Apple — in stock, checked 19 minutes ago.

Price history: 47 days recorded.

Offers — Mac mini, M6, 24GB, 512GB

Applelist pricein stockchecked 19 minutes ago$1,299
Best BuyApple's own price, to the cent.in stockchecked 46 days ago$1,299
ExpercomApple's own price, to the cent.in stockchecked 18 days ago$1,299

Mac mini, M6, 16GB$1,099
Won't fit−3GB headroom
Mac mini, M6, 24GB$1,299
Fits5GB headroomest. 33.3 tok/s
Mac mini, M6, 32GB$1,499
Fits13GB headroomest. 33.3 tok/s
Mac mini, M5 Pro, 24GB$1,699
Fits5GB headroomest. 60.2 tok/s
Mac mini, M5 Pro, 48GB$2,499
Fits28GB headroomest. 60.2 tok/s
Mac Studio, M5 Max, 36GB$2,499
Fits17GB headroomest. 90.1 tok/s
Mac mini, M5 Pro, 64GB$2,899
Fits42GB headroomest. 60.2 tok/s
GeForce RTX 5090, 32GB$2,999.99+host
Fits14GB headroomest. 351 tok/s
Mac Studio, M4 Max, 64GB, refurbished$3,049
Fits42GB headroomest. 107 tok/s
Mac Studio, M5 Max, 48GB$3,099
Fits28GB headroomest. 120 tok/s
Mac Studio, M5 Max, 64GB$3,499
Fits42GB headroomest. 120 tok/s
Ascent GX10, GB10 Grace Blackwell, 128GB$3,999.99
Fits104GB headroomest. 53.5 tok/s
Mac Studio, M3 Ultra, 96GB, refurbished$4,329
Fits72GB headroomest. 160 tok/s
Mac Studio, M4 Max, 128GB, refurbished$4,409
Fits104GB headroomest. 107 tok/s
DGX Spark, GB10 Grace Blackwell, 128GB$4,699
Fits104GB headroomest. 53.5 tok/s
Mac Studio, M5 Max, 128GB$5,099
Fits104GB headroomest. 120 tok/s
Mac Studio, M5 Ultra, 96GB$5,499
Fits72GB headroomest. 235 tok/s
Mac Studio, M3 Ultra, 256GB, refurbished$7,729
Fits232GB headroomest. 160 tok/s
Mac Studio, M5 Ultra, 256GB$9,499
Fits232GB headroomest. 235 tok/s
Mac Studio, M5 Ultra, 512GB—
Fits488GB headroomest. 235 tok/s

Config	Memory	Price	Fit	Headroom	Est. speed
Mac mini, M6	16GB	$1,099	Won't fit	−3GB	—
Mac mini, M6	24GB	$1,299	Fits	5GB	33.3 tok/s
Mac mini, M6	32GB	$1,499	Fits	13GB	33.3 tok/s
Mac mini, M5 Pro	24GB	$1,699	Fits	5GB	60.2 tok/s
Mac mini, M5 Pro	48GB	$2,499	Fits	28GB	60.2 tok/s
Mac Studio, M5 Max	36GB	$2,499	Fits	17GB	90.1 tok/s
Mac mini, M5 Pro	64GB	$2,899	Fits	42GB	60.2 tok/s
GeForce RTX 5090	32GB	$2,999.99+host	Fits	14GB	351 tok/s
Mac Studio, M4 Max, refurb	64GB	$3,049	Fits	42GB	107 tok/s
Mac Studio, M5 Max	48GB	$3,099	Fits	28GB	120 tok/s
Mac Studio, M5 Max	64GB	$3,499	Fits	42GB	120 tok/s
Ascent GX10, GB10 Grace Blackwell	128GB	$3,999.99	Fits	104GB	53.5 tok/s
Mac Studio, M3 Ultra, refurb	96GB	$4,329	Fits	72GB	160 tok/s
Mac Studio, M4 Max, refurb	128GB	$4,409	Fits	104GB	107 tok/s
DGX Spark, GB10 Grace Blackwell	128GB	$4,699	Fits	104GB	53.5 tok/s
Mac Studio, M5 Max	128GB	$5,099	Fits	104GB	120 tok/s
Mac Studio, M5 Ultra	96GB	$5,499	Fits	72GB	235 tok/s
Mac Studio, M3 Ultra, refurb	256GB	$7,729	Fits	232GB	160 tok/s
Mac Studio, M5 Ultra	256GB	$9,499	Fits	232GB	235 tok/s
Mac Studio, M5 Ultra	512GB	—	Fits	488GB	235 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 × 0.709 B/param (5.67 bits) + 0.049 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3.6B active × 0.709 B/param) = 2.6 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 24GB runs

Qwen3.5-35B-A3BQ3_K_M, est. 58.0 tok/s
Qwen3-32BQ3_K_M, est. 7.1 tok/s
Gemma-4-31BQ3_K_M, est. 7.4 tok/s
Qwen3-30B-A3BQ4_K_M, est. 42.7 tok/s
Gemma-3-27BQ4_K_M, est. 6.8 tok/s
Qwen3.6-27BQ5_K_M, est. 5.8 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.