Qwen3.6 35B-A3B hardware requirements

About the model

Parameters: 35.95B total · 3B active (MoE)
Attention: Hybrid linear attention
Max context: 262,144 tokens
Released: 2026-04-15
Model card: Qwen3.6 35B-A3B on Hugging Face

GGUF files

Tracked quantizations of Qwen3.6 35B-A3B, smallest first
Quant	File size	Quality	Published by
Q2_K	13.51 GB	Heavy loss	Community GGUF · bartowski
IQ4_XS	19.70 GB	Good balance	Community GGUF · bartowski
Q4_K_Mbaseline	22.29 GB	Good balance	Community GGUF · bartowski
Q8_0	37.81 GB	Near-lossless	Community GGUF · bartowski

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
Q2_K	14.1	14.3	14.5	15.0	16.0	17.9	21.8
IQ4_XS	20.3	20.4	20.7	21.2	22.1	24.1	28.0
Q4_K_M	22.9	23.0	23.3	23.8	24.7	26.7	30.6
Q8_0	38.4	38.6	38.8	39.3	40.3	42.2	46.1

Which GPUs can run Qwen3.6 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	23.6 / 32.0 GB	Full GPU	up to 256k	—	$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 235.0 tok/s188.0–282.0calibrated estimate ±20%	Q4_K_M	23.6 / 24.0 GB	Full GPU	up to 16k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 223.7 tok/s178.9–268.4calibrated estimate ±20%	Q4_K_M	23.6 / 24.0 GB	Full GPU	up to 16k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 223.7 tok/s178.9–268.4calibrated estimate ±20%	Q4_K_M	23.6 / 24.0 GB	Full GPU	up to 16k	—	$2,755 street (as of 2026-08-09)
GeForce RTX 3090	Runs great	est. 207.7 tok/s166.2–249.2calibrated estimate ±20%	Q4_K_M	23.6 / 24.0 GB	Full GPU	up to 16k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5090 Laptop	Runs great	est. 198.8 tok/s159.1–238.6calibrated estimate ±20%	Q4_K_M	23.6 / 24.0 GB	Full GPU	up to 16k	—	—
Apple M3 Ultra · 96 GB	Runs great	est. 117.1 tok/s93.7–140.5calibrated estimate ±20%	Q4_K_M	23.0 / 67.2 GB	Unified memory	up to 256k	—	—
Apple M2 Ultra · 64 GB	Runs great	est. 114.4 tok/s91.5–137.3calibrated estimate ±20%	Q4_K_M	23.0 / 44.8 GB	Unified memory	up to 256k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 90.8 tok/s72.7–109.0calibrated estimate ±20%	Q4_K_M	23.0 / 33.6 GB	Unified memory	up to 256k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs great	est. 80.8 tok/s64.6–96.9calibrated estimate ±20%	Q4_K_M	23.0 / 33.6 GB	Unified memory	up to 256k	—	—
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 68.1 tok/s54.4–81.7calibrated estimate ±20%	Q4_K_M	23.0 / 25.2 GB	Unified memory	up to 64k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 64 GB	Runs great	est. 66.9 tok/s53.5–80.3calibrated estimate ±20%	Q4_K_M	23.0 / 44.8 GB	Unified memory	up to 128k	—	$1,999 launch MSRP
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 60.7 tok/s48.5–72.8calibrated estimate ±20%	Q4_K_M	23.0 / 25.2 GB	Unified memory	up to 64k	—	—
NVIDIA DGX Spark · 128 GB	Runs great	est. 53.8 tok/s43.1–64.6calibrated estimate ±20%	Q4_K_M	23.0 / 89.6 GB	Unified memory	up to 128k	—	$3,999 launch MSRP
Apple M5 Pro · 48 GB	Runs great	est. 45.4 tok/s36.3–54.5calibrated estimate ±20%	Q4_K_M	23.0 / 33.6 GB	Unified memory	up to 128k	—	—
Apple M4 Pro · 48 GB	Runs great	est. 40.4 tok/s32.3–48.5calibrated estimate ±20%	Q4_K_M	23.0 / 33.6 GB	Unified memory	up to 64k	—	—
Intel Arc B580	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 11.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 11.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 10.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$499 launch MSRP
GeForce RTX 4060 Ti 8GB	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$799 launch MSRP
GeForce RTX 4080	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$1,199 launch MSRP
GeForce RTX 4080 Laptop	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$999 launch MSRP
GeForce RTX 4090 Laptop	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	—
GeForce RTX 5060	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$569 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 8.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$949 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 12.0 GB + 21.1 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. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$1,256 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	—
Radeon RX 7800 XT	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$499 launch MSRP
Radeon RX 7900 XT	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 20.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$899 launch MSRP
Radeon RX 9060 XT 16GB	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$449 street (as of 2026-08-09)
Radeon RX 9070	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs well	est. 20.7 tok/s14.5–26.9theoretical estimate ±30%	Q4_K_M	2.5 / 16.0 GB + 21.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Q2_K (heavy quality loss): Runs great	$689 street (as of 2026-08-09)
Apple M5 · 32 GB	Runs slowly	est. 22.7 tok/s15.9–29.5theoretical estimate ±30%	Q4_K_M	22.5 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. 20.4 tok/s16.3–24.4calibrated estimate ±20%	Q4_K_M	22.5 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
DDR5-5600 dual-channel CPU · 32 GB	Runs slowly	est. 19.0 tok/s15.2–22.8calibrated estimate ±20%	Q4_K_M	22.5 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
Apple M4 · 32 GB	Runs slowly	est. 17.8 tok/s12.4–23.1theoretical estimate ±30%	Q4_K_M	22.5 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great	—
DDR4-3200 dual-channel CPU · 32 GB	Runs slowly	est. 10.9 tok/s8.7–13.0calibrated estimate ±20%	Q4_K_M	22.5 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. 207.7 tok/s (166.2–249.2, calibrated estimate ±20%).
Runs wellGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 20.7 tok/s (14.5–26.9, theoretical estimate ±30%).

Measured results for Qwen3.6 35B-A3B

Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.

Measured results for Qwen3.6 35B-A3B
Hardware	Quant	Backend	Context	Prompt (tok/s)	Generation (tok/s)	Flags	Source	Measured
GeForce RTX 3060 12GB	Q4_K_M	llama.cpp	4k	—	52.0	--n-cpu-moe, DDR5	openclawdc.com	2026-07-15

Frequently asked questions

How much VRAM does Qwen3.6 35B-A3B need?

At Q4_K_M the weights are 22.29 GB; with 8k context the total is about 23.0 GB (KV cache 0.2 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 14.3 GB.

What is the cheapest GPU that runs Qwen3.6 35B-A3B well?

Cheapest that runs it great: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 207.7 tok/s (166.2–249.2, calibrated estimate ±20%). Cheaper and still Runs well: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 20.7 tok/s (14.5–26.9, theoretical estimate ±30%).

Can Qwen3.6 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. 20.7 tok/s (14.5–26.9, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs well, est. 20.7 tok/s (14.5–26.9, theoretical estimate ±30%); GeForce RTX 3090 — Runs great, est. 207.7 tok/s (166.2–249.2, 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.