How much memory does Qwen3.5-35B-A3B at Q5_K_M need?

26GB. That is 25GB of weights at 5.67 bits per weight, 0.2GB of K/V cache at 8K context, and 1.2GB of runtime overhead.

Which machine is cheapest for Qwen3.5-35B-A3B at Q5_K_M?

Mac mini, M5 Pro, 48GB, $2,499 at Apple. It fits with 18GB of headroom and decodes at an est. 72.2 tok/s.

Cheapest box to run Qwen3.5-35B-A3B at Q5_K_M

Alibaba’s Qwen3.5-35B-A3B is 35B parameters, 3B 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 32 minutes ago

Quant

Context

Qwen3.5-35B-A3B at Q5_K_M needs 26GB.

Cheapest Config that fits: Mac mini, M5 Pro, 48GB. Fits, 18GB headroom. Est. 72.2 tok/s.

Best offer today: $2,499 at Apple — in stock, checked 32 minutes ago.

Price history: 34 days recorded.

A hybrid: only 10 of 40 layers are full attention. The Gated DeltaNet layers keep a constant-size state and cache nothing per token, so the K/V figure counts the full-attention layers alone.

Offers — Mac mini, M5 Pro, 48GB, 512GB

Applelist pricein stockchecked 32 minutes ago$2,499

Mac mini, M6, 16GB$1,099
Won't fit−13GB headroom
Mac mini, M6, 24GB$1,299
Won't fit−5GB headroom
Mac mini, M6, 32GB$1,499
Tight3GB headroomest. 40.0 tok/s
Mac mini, M5 Pro, 24GB$1,699
Won't fit−5GB headroom
Mac mini, M5 Pro, 48GB$2,499
Fits18GB headroomest. 72.2 tok/s
Mac Studio, M5 Max, 36GB$2,499
Fits7GB headroomest. 108 tok/s
Mac mini, M5 Pro, 64GB$2,899
Fits33GB headroomest. 72.2 tok/s
GeForce RTX 5090, 32GB$2,999.99+host
Fits5GB headroomest. 421 tok/s
Mac Studio, M4 Max, 64GB, refurbished$3,049
Fits33GB headroomest. 128 tok/s
Mac Studio, M5 Max, 48GB$3,099
Fits18GB headroomest. 144 tok/s
Mac Studio, M5 Max, 64GB$3,499
Fits33GB headroomest. 144 tok/s
Ascent GX10, GB10 Grace Blackwell, 128GB$3,999.99
Fits94GB headroomest. 64.2 tok/s
Mac Studio, M3 Ultra, 96GB, refurbished$4,329
Fits62GB headroomest. 193 tok/s
Mac Studio, M4 Max, 128GB, refurbished$4,409
Fits94GB headroomest. 128 tok/s
DGX Spark, GB10 Grace Blackwell, 128GB$4,699
Fits94GB headroomest. 64.2 tok/s
Mac Studio, M5 Max, 128GB$5,099
Fits94GB headroomest. 144 tok/s
Mac Studio, M5 Ultra, 96GB$5,499
Fits62GB headroomest. 282 tok/s
Mac Studio, M3 Ultra, 256GB, refurbished$7,729
Fits222GB headroomest. 193 tok/s
Mac Studio, M5 Ultra, 256GB$9,499
Fits222GB headroomest. 282 tok/s
Mac Studio, M5 Ultra, 512GB—
Fits478GB headroomest. 282 tok/s

Config	Memory	Price	$/GB	Fit	Headroom	Est. speed
Mac mini, M6	16GB	$1,099	$69	Won't fit	−13GB	—
Mac mini, M6	24GB	$1,299	$54	Won't fit	−5GB	—
Mac mini, M6	32GB	$1,499	$47	Tight	3GB	40.0 tok/s
Mac mini, M5 Pro	24GB	$1,699	$71	Won't fit	−5GB	—
Mac mini, M5 Pro	48GB	$2,499	$52	Fits	18GB	72.2 tok/s
Mac Studio, M5 Max	36GB	$2,499	$69	Fits	7GB	108 tok/s
Mac mini, M5 Pro	64GB	$2,899	$45	Fits	33GB	72.2 tok/s
GeForce RTX 5090	32GB	$2,999.99+host	$94	Fits	5GB	421 tok/s
Mac Studio, M4 Max, refurb	64GB	$3,049	$48	Fits	33GB	128 tok/s
Mac Studio, M5 Max	48GB	$3,099	$65	Fits	18GB	144 tok/s
Mac Studio, M5 Max	64GB	$3,499	$55	Fits	33GB	144 tok/s
Ascent GX10, GB10 Grace Blackwell	128GB	$3,999.99	$31	Fits	94GB	64.2 tok/s
Mac Studio, M3 Ultra, refurb	96GB	$4,329	$45	Fits	62GB	193 tok/s
Mac Studio, M4 Max, refurb	128GB	$4,409	$34	Fits	94GB	128 tok/s
DGX Spark, GB10 Grace Blackwell	128GB	$4,699	$37	Fits	94GB	64.2 tok/s
Mac Studio, M5 Max	128GB	$5,099	$40	Fits	94GB	144 tok/s
Mac Studio, M5 Ultra	96GB	$5,499	$57	Fits	62GB	282 tok/s
Mac Studio, M3 Ultra, refurb	256GB	$7,729	$30	Fits	222GB	193 tok/s
Mac Studio, M5 Ultra	256GB	$9,499	$37	Fits	222GB	282 tok/s
Mac Studio, M5 Ultra	512GB	—	—	Fits	478GB	282 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 = 35B × 0.709 B/param (5.67 bits) + 0.021 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3B active × 0.709 B/param) = 2.1 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 M5 Pro 48GB runs

Qwen3-Coder-NextQ3_K_M, est. 105 tok/s
Llama-3.3-70BQ3_K_M, est. 5.8 tok/s
Qwen3.5-35B-A3BQ8_0, est. 48.2 tok/s
Qwen3-32BQ8_0, est. 5.9 tok/s
Gemma-4-31BQ8_0, est. 6.1 tok/s
Qwen3-30B-A3BQ8_0, est. 43.8 tok/s

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

Bandwidth 307GB/s, usable memory 44GB of 48GB.