Qwen3.5 35B-A3B hardware requirements

About the model

Parameters: 35.95B total · 3B active (MoE)
Attention: Hybrid linear attention
Max context: 262,144 tokens
Released: 2026-05-01
Model card: Qwen3.5 35B-A3B on Hugging Face

GGUF files

Tracked quantizations of Qwen3.5 35B-A3B, smallest first
Quant	File size	Quality	Published by
UD-Q2_K_XL	12.57 GB	Heavy loss	Community GGUF · unsloth
IQ4_XS	18.17 GB	Good balance	Community GGUF · unsloth
Q4_K_Mbaseline	22.63 GB	Good balance	Community GGUF · unsloth
Q8_0	37.80 GB	Near-lossless	Community GGUF · unsloth

Some repositories publish only Unsloth Dynamic (UD) variants; sizes are those of the file you would download.

Memory needed by quant and context

Weights + f16 KV cache + compute buffer, in GB. Add about 0.6 GB if the GPU also drives your display on Windows.
Quant	4k	8k	16k	32k	64k	128k	256k
UD-Q2_K_XL	13.2	13.3	13.6	14.0	15.0	17.0	20.8
IQ4_XS	18.8	18.9	19.2	19.6	20.6	22.6	26.4
Q4_K_M	23.3	23.4	23.6	24.1	25.1	27.0	30.9
Q8_0	38.4	38.5	38.8	39.3	40.2	42.2	46.1

Which GPUs can run Qwen3.5 35B-A3B?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Sort

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs great	est. 235.0 tok/s188.0–282.0calibrated estimate ±20%	Q4_K_M	24.0 / 32.0 GB	Full GPU	up to 256k	—	$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 233.4 tok/s186.7–280.1calibrated estimate ±20%	Q4_K_M	24.0 / 24.0 GB	Full GPU	up to 8k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 220.6 tok/s176.5–264.7calibrated estimate ±20%	Q4_K_M	24.0 / 24.0 GB	Full GPU	up to 8k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 220.6 tok/s176.5–264.7calibrated estimate ±20%	Q4_K_M	24.0 / 24.0 GB	Full GPU	up to 8k	—	$2,755 street (as of 2026-08-09)
GeForce RTX 3090	Runs great	est. 204.8 tok/s163.9–245.8calibrated estimate ±20%	Q4_K_M	24.0 / 24.0 GB	Full GPU	up to 8k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5090 Laptop	Runs great	est. 196.1 tok/s156.9–235.3calibrated estimate ±20%	Q4_K_M	24.0 / 24.0 GB	Full GPU	up to 8k	—	—
Apple M3 Ultra · 96 GB	Runs great	est. 115.5 tok/s92.4–138.6calibrated estimate ±20%	Q4_K_M	23.4 / 67.2 GB	Unified memory	up to 256k	—	—
Apple M2 Ultra · 64 GB	Runs great	est. 112.8 tok/s90.3–135.4calibrated estimate ±20%	Q4_K_M	23.4 / 44.8 GB	Unified memory	up to 256k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 89.6 tok/s71.7–107.5calibrated estimate ±20%	Q4_K_M	23.4 / 33.6 GB	Unified memory	up to 256k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs great	est. 79.7 tok/s63.7–95.6calibrated estimate ±20%	Q4_K_M	23.4 / 33.6 GB	Unified memory	up to 256k	—	—
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 67.1 tok/s53.7–80.5calibrated estimate ±20%	Q4_K_M	23.4 / 25.2 GB	Unified memory	up to 64k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 64 GB	Runs great	est. 66.0 tok/s52.8–79.2calibrated estimate ±20%	Q4_K_M	23.4 / 44.8 GB	Unified memory	up to 128k	—	$1,999 launch MSRP
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 59.8 tok/s47.9–71.8calibrated estimate ±20%	Q4_K_M	23.4 / 25.2 GB	Unified memory	up to 64k	—	—
NVIDIA DGX Spark · 128 GB	Runs great	est. 53.1 tok/s42.5–63.7calibrated estimate ±20%	Q4_K_M	23.4 / 89.6 GB	Unified memory	up to 128k	—	$3,999 launch MSRP
Apple M5 Pro · 48 GB	Runs great	est. 44.8 tok/s35.8–53.7calibrated estimate ±20%	Q4_K_M	23.4 / 33.6 GB	Unified memory	up to 128k	—	—
Apple M4 Pro · 48 GB	Runs great	est. 39.8 tok/s31.9–47.8calibrated estimate ±20%	Q4_K_M	23.4 / 33.6 GB	Unified memory	up to 64k	—	—
Intel Arc B580	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$290 street (as of 2026-08-09)
GeForce GTX 1080 Ti	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 11.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$699 launch MSRP
GeForce RTX 2080 Ti	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 11.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$999 launch MSRP
GeForce RTX 3050 8GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$249 launch MSRP
GeForce RTX 3060 12GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$250 street (as of 2026-08-09)
GeForce RTX 3070	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$499 launch MSRP
GeForce RTX 3080 10GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 10.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$699 launch MSRP
GeForce RTX 3080 12GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$799 launch MSRP
GeForce RTX 4060	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 4060 Ti 16GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$499 launch MSRP
GeForce RTX 4060 Ti 8GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$399 launch MSRP
GeForce RTX 4070	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$599 launch MSRP
GeForce RTX 4070 Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 4070 Super	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$599 launch MSRP
GeForce RTX 4070 Ti Super	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$799 launch MSRP
GeForce RTX 4080	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$1,199 launch MSRP
GeForce RTX 4080 Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 4080 Super	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$999 launch MSRP
GeForce RTX 4090 Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	—
GeForce RTX 5060	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 16GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$569 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 8.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$429 street (as of 2026-08-09)
GeForce RTX 5070	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$949 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 12.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 5080	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$1,256 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	—
Radeon RX 7800 XT	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$499 launch MSRP
Radeon RX 7900 XT	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 20.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Try IQ4_XS: Runs great	$899 launch MSRP
Radeon RX 9060 XT 16GB	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$449 street (as of 2026-08-09)
Radeon RX 9070	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs well	est. 20.4 tok/s14.3–26.5theoretical estimate ±30%	Q4_K_M	2.6 / 16.0 GB + 21.4 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory UD-Q2_K_XL (heavy quality loss): Runs great	$689 street (as of 2026-08-09)
Apple M5 · 32 GB	Runs slowly	est. 22.4 tok/s15.7–29.1theoretical estimate ±30%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly Try IQ4_XS: Runs great	—
DDR5-6000 dual-channel CPU · 32 GB	Runs slowly	est. 20.1 tok/s16.1–24.1calibrated estimate ±20%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
DDR5-5600 dual-channel CPU · 32 GB	Runs slowly	est. 18.7 tok/s15.0–22.5calibrated estimate ±20%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
Apple M4 · 32 GB	Runs slowly	est. 17.5 tok/s12.3–22.8theoretical estimate ±30%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly Try IQ4_XS: Runs great	—
DDR4-3200 dual-channel CPU · 32 GB	Runs slowly	est. 10.7 tok/s8.6–12.8calibrated estimate ±20%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—

Cheapest GPUs that run it

Runs greatGeForce RTX 3090$1,050 street (as of 2026-08-09), est. 204.8 tok/s (163.9–245.8, calibrated estimate ±20%).
Runs wellGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 20.4 tok/s (14.3–26.5, theoretical estimate ±30%).

Measured results for Qwen3.5 35B-A3B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Qwen3.5 35B-A3B need?

At Q4_K_M the weights are 22.63 GB; with 8k context the total is about 23.4 GB (KV cache 0.2 GB, compute buffer 0.6 GB). The smallest tracked file (UD-Q2_K_XL (heavy quality loss)) needs about 13.3 GB.

What is the cheapest GPU that runs Qwen3.5 35B-A3B well?

Cheapest that runs it great: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 204.8 tok/s (163.9–245.8, calibrated estimate ±20%). Cheaper and still Runs well: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 20.4 tok/s (14.3–26.5, theoretical estimate ±30%).

Can Qwen3.5 35B-A3B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs well, est. 20.4 tok/s (14.3–26.5, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs well, est. 20.4 tok/s (14.3–26.5, theoretical estimate ±30%); GeForce RTX 3090 — Runs great, est. 204.8 tok/s (163.9–245.8, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.