How much memory does Gemma-3-27B at Q5_K_M need?

22GB. That is 19GB of weights at 5.67 bits per weight, 2.0GB of K/V cache at 8K context, and 1.2GB of runtime overhead.

Which machine is cheapest for Gemma-3-27B at Q5_K_M?

Mac mini, M6, 32GB, $1,499 at Apple. It fits with 7GB of headroom and decodes at an est. 5.8 tok/s.

Cheapest box to run Gemma-3-27B at Q5_K_M

Google’s Gemma-3-27B is 27B 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.

Fit finderprices checked 10 hours ago

Quant

Context

Gemma-3-27B at Q5_K_M needs 22GB.

Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 7GB headroom. Est. 5.8 tok/s.

Best offer today: $1,499 at Apple — in stock, checked 10 hours ago.

Collecting price history — 2 of 90 days. No timing verdict yet.

Offers — Mac mini, M6, 32GB, 512GB

Applelist pricein stockchecked 10 hours ago$1,499
Expercomout of stockchecked 10 hours ago$1,499
B&H Photoout of stockchecked 10 hours ago$1,599

Mac mini, M6, 16GB$1,099
Won't fit−9GB headroom
Mac mini, M6, 24GB$1,299
Won't fit−1GB headroom
Mac mini, M6, 32GB$1,499
Fits7GB headroomest. 5.8 tok/s
Mac mini, M5 Pro, 24GB$1,699
Won't fit−1GB headroom
Mac mini, M5 Pro, 48GB$2,499
Fits22GB headroomest. 10.4 tok/s
Mac Studio, M5 Max, 36GB$2,499
Fits11GB headroomest. 20.9 tok/s
Mac mini, M5 Pro, 64GB$2,899
Fits37GB headroomest. 10.4 tok/s
GeForce RTX 5090, 32GB$2,999.99+host
Fits8GB headroomest. 60.9 tok/s
Mac Studio, M5 Max, 48GB$3,099
Fits22GB headroomest. 20.9 tok/s
Mac Studio, M5 Max, 64GB$3,499
Fits37GB headroomest. 20.9 tok/s
Ascent GX10, GB10 Grace Blackwell, 128GB$3,999.99
Fits98GB headroomest. 9.3 tok/s
DGX Spark, GB10 Grace Blackwell, 128GB$4,699
Fits98GB headroomest. 9.3 tok/s
Mac Studio, M5 Max, 128GB$5,099
Fits98GB headroomest. 20.9 tok/s
Mac Studio, M5 Ultra, 96GB$5,499
Fits66GB headroomest. 40.8 tok/s
Mac Studio, M5 Ultra, 256GB$9,499
Fits226GB headroomest. 40.8 tok/s
Mac Studio, M5 Ultra, 512GB—
Fits482GB headroomest. 40.8 tok/s

Config	Memory	Price	$/GB	Fit	Headroom	Est. speed
Mac mini, M6	16GB	$1,099	$69	Won't fit	−9GB	—
Mac mini, M6	24GB	$1,299	$54	Won't fit	−1GB	—
Mac mini, M6	32GB	$1,499	$47	Fits	7GB	5.8 tok/s
Mac mini, M5 Pro	24GB	$1,699	$71	Won't fit	−1GB	—
Mac mini, M5 Pro	48GB	$2,499	$52	Fits	22GB	10.4 tok/s
Mac Studio, M5 Max	36GB	$2,499	$69	Fits	11GB	20.9 tok/s
Mac mini, M5 Pro	64GB	$2,899	$45	Fits	37GB	10.4 tok/s
GeForce RTX 5090	32GB	$2,999.99+host	$94	Fits	8GB	60.9 tok/s
Mac Studio, M5 Max	48GB	$3,099	$65	Fits	22GB	20.9 tok/s
Mac Studio, M5 Max	64GB	$3,499	$55	Fits	37GB	20.9 tok/s
Ascent GX10, GB10 Grace Blackwell	128GB	$3,999.99	$31	Fits	98GB	9.3 tok/s
DGX Spark, GB10 Grace Blackwell	128GB	$4,699	$37	Fits	98GB	9.3 tok/s
Mac Studio, M5 Max	128GB	$5,099	$40	Fits	98GB	20.9 tok/s
Mac Studio, M5 Ultra	96GB	$5,499	$57	Fits	66GB	40.8 tok/s
Mac Studio, M5 Ultra	256GB	$9,499	$37	Fits	226GB	40.8 tok/s
Mac Studio, M5 Ultra	512GB	—	—	Fits	482GB	40.8 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 = 27B × 0.709 B/param (5.67 bits) + 0.254 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (27B active × 0.709 B/param) = 19.1 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 32GB runs

Qwen3-32BQ5_K_M, est. 4.9 tok/s
Gemma-3-27BQ6_K, est. 5.0 tok/s
gpt-oss-20bQ8_0, est. 22.2 tok/s

Best quant that still fits at 8K context, largest model first. Full list on the Config page.

Bandwidth 170GB/s, usable memory 29GB of 32GB.