Qwen3 14B hardware requirements

What is Qwen3 14B?

Qwen3 14B is the second-largest dense model in the Qwen3 family, which Alibaba Cloud's Qwen team released in April 2025. It thinks before answering by default, and adding /no_think to a message makes it reply directly instead. The model card highlights reasoning, coding, multilingual instruction following and tool use for agents.

Model card

What to know before running Qwen3 14B

Qwen3 14B is the model that separates 8GB cards from 12GB ones. At Q4_K_M it needs 10.5 GB with an 8k context: a 12GB card holds it completely, while on an 8GB card part of it moves to system RAM and it runs slowly. Even the smaller IQ4_XS file does not fit in 8GB. Our page for Qwen3 14B on the GeForce RTX 4060 shows the numbers.

It thinks before answering by default, so CanRun holds it to a 1.5× stricter speed bar, and the speed of the card decides the grade among 12GB cards. The GeForce RTX 4070 runs it great; the slower GeForce RTX 3060 12GB holds it just as completely but runs it well. You can switch thinking off as the Qwen3-14B model card describes, and then it may do one grade better.

On a 16GB card such as the GeForce RTX 5060 Ti 16GB, there is room for its full 32k context on the GPU. On a Mac, the 24GB Apple M4 Pro runs it well.

About the model

Parameters: 14.8B
Attention: Full attention
Max context: 32,768 tokens
Released: 2025-04-29
Model card: Qwen3 14B on Hugging Face

Other sizes in this series

Graphics card memory each model needs at its baseline quant with 8k context, and its verdict on common graphics cards, smallest model first
Model	Parameters	Baseline quant	Memory needed (8k)	GeForce RTX 4060	GeForce RTX 5060 Ti 16GB	GeForce RTX 3090
Qwen3 8B	8.2B	Q4_K_M	6.5 GB	Runs great	Runs great	Runs great
Qwen3 14Bthis model	14.8B	Q4_K_M	10.5 GB	Runs slowly	Runs great	Runs great
Qwen3 30B-A3B (2507)	30.5B total · 3.3B active (MoE)	Q4_K_M	19.8 GB	Runs well	Runs well	Runs great
Qwen3 32B	32.8B	Q4_K_M	22.0 GB	Won't run	Runs slowly	Runs well

GGUF files

Tracked quantizations of Qwen3 14B, smallest first
Quant	File size	Quality	Published by
Q2_K	5.75 GB	Heavy loss	Community GGUF · unsloth
IQ4_XS	8.14 GB	Good balance	Community GGUF · unsloth
Q4_K_Mbaseline	9.00 GB	Good balance	Community GGUF · unsloth
Q8_0	15.70 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

Graphics card memory in GB: weights loaded on the GPU + f16 KV cache + compute buffer. Add about 0.6 GB if the GPU also drives your display on Windows. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
Quant	4k	8k	16k	32k
Q2_K	6.7	7.4	8.8	11.7
IQ4_XS	8.9	9.6	11.0	13.9
Q4_K_M	9.8	10.5	11.9	14.7
Q8_0	16.1	16.8	18.2	21.0

Which GPUs can run Qwen3 14B?

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

Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.

Sort

Filter this list by budget, type and context in the calculator

Scroll sideways to see every column.

58 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 greatQwen3 14B verdict on the GeForce RTX 5090	est. 121.3 tok/s106.7–135.8calibrated estimate ±12%	Q4_K_M	11.1 / 32.0 GB	Full GPU	up to 32k	—	$4,200 street (as of 2026-08-09)
NVIDIA RTX PRO 6000 Blackwell	Runs great	est. 121.3 tok/s106.7–135.8calibrated estimate ±12%	Q4_K_M	11.1 / 96.0 GB	Full GPU	up to 32k	—	—
NVIDIA RTX PRO 6000 Blackwell Max-Q	Runs great	est. 121.3 tok/s106.7–135.8calibrated estimate ±12%	Q4_K_M	11.1 / 96.0 GB	Full GPU	up to 32k	—	—
Radeon RX 7900 XTX	Runs great	est. 70.5 tok/s62.1–79.0calibrated estimate ±12%	Q4_K_M	11.1 / 24.0 GB	Full GPU	up to 32k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 68.2 tok/s60.0–76.4calibrated estimate ±12%	Q4_K_M	11.1 / 24.0 GB	Full GPU	up to 32k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs greatQwen3 14B verdict on the GeForce RTX 4090	est. 68.2 tok/s60.0–76.4calibrated estimate ±12%	Q4_K_M	11.1 / 24.0 GB	Full GPU	up to 32k	—	$2,755 street (as of 2026-08-09)
Apple M5 Ultra · 96 GB	Runs great	est. 67.7 tok/s54.1–81.2calibrated estimate ±20%	Q4_K_M	10.9 / 67.2 GB	Unified memory	up to 32k	—	—
GeForce RTX 5080	Runs great	est. 65.0 tok/s57.2–72.8calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$1,256 street (as of 2026-08-09)
GeForce RTX 3090	Runs greatQwen3 14B verdict on the GeForce RTX 3090	est. 63.4 tok/s55.7–71.0calibrated estimate ±12%	Q4_K_M	11.1 / 24.0 GB	Full GPU	up to 32k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 3080 12GB	Runs great	est. 61.7 tok/s54.3–69.1calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	—	$799 launch MSRP
GeForce RTX 5070 Ti	Runs great	est. 60.6 tok/s53.4–67.9calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs great	est. 60.6 tok/s53.4–67.9calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	—
GeForce RTX 5090 Laptop	Runs great	est. 60.6 tok/s53.4–67.9calibrated estimate ±12%	Q4_K_M	11.1 / 24.0 GB	Full GPU	up to 32k	—	—
Radeon RX 7900 XT	Runs great	est. 58.8 tok/s51.7–65.8calibrated estimate ±12%	Q4_K_M	11.1 / 20.0 GB	Full GPU	up to 32k	—	$899 launch MSRP
GeForce RTX 4080 Super	Runs great	est. 49.8 tok/s43.8–55.8calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$999 launch MSRP
GeForce RTX 4080	Runs great	est. 48.5 tok/s42.7–54.4calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$1,199 launch MSRP
Radeon RX 9070	Runs great	est. 47.4 tok/s41.7–53.1calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs great	est. 47.4 tok/s41.7–53.1calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$689 street (as of 2026-08-09)
Radeon RX 7800 XT	Runs great	est. 45.9 tok/s40.4–51.4calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$499 launch MSRP
GeForce RTX 4070 Ti Super	Runs great	est. 45.5 tok/s40.0–50.9calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$799 launch MSRP
GeForce RTX 5070	Runs greatQwen3 14B verdict on the GeForce RTX 5070	est. 45.5 tok/s40.0–50.9calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	—	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs great	est. 45.5 tok/s40.0–50.9calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	—	—
Apple M3 Ultra · 96 GB	Runs great	est. 45.1 tok/s36.1–54.2calibrated estimate ±20%	Q4_K_M	10.9 / 67.2 GB	Unified memory	up to 32k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 45.1 tok/s36.1–54.1calibrated estimate ±20%	Q4_K_M	10.9 / 33.6 GB	Unified memory	up to 32k	—	—
Apple M2 Ultra · 64 GB	Runs great	est. 44.1 tok/s35.3–52.9calibrated estimate ±20%	Q4_K_M	10.9 / 44.8 GB	Unified memory	up to 32k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs great	est. 40.1 tok/s32.1–48.1calibrated estimate ±20%	Q4_K_M	10.9 / 33.6 GB	Unified memory	up to 16k	—	—
GeForce RTX 4090 Laptop	Runs great	est. 39.0 tok/s34.3–43.7calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 16k	—	—
GeForce RTX 4070	Runs greatQwen3 14B verdict on the GeForce RTX 4070	est. 34.1 tok/s30.0–38.2calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	—	$599 launch MSRP
GeForce RTX 4070 Super	Runs great	est. 34.1 tok/s30.0–38.2calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	—	$599 launch MSRP
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 33.8 tok/s27.0–40.6calibrated estimate ±20%	Q4_K_M	10.9 / 25.2 GB	Unified memory	up to 8k	—	—
GeForce RTX 5060 Ti 16GB	Runs greatQwen3 14B verdict on the GeForce RTX 5060 Ti 16GB	est. 30.3 tok/s26.7–34.0calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 8k	—	$569 street (as of 2026-08-09)
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 30.1 tok/s24.1–36.2calibrated estimate ±20%	Q4_K_M	10.9 / 25.2 GB	Unified memory	up to 8k	—	—
GeForce RTX 4080 Laptop	Runs well	est. 29.2 tok/s25.7–32.7calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	Try IQ4_XS: Runs great	—
GeForce RTX 2080 Ti	Runs well	est. 27.9 tok/s22.3–33.5calibrated estimate ±20%	Q4_K_M	11.0 / 11.0 GB + 0.5 GB RAM	Partial offload	up to 8k	Try IQ4_XS: Runs great	$999 launch MSRP
Intel Arc B580	Runs well	est. 26.0 tok/s20.8–31.2calibrated estimate ±20%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	Q2_K (heavy quality loss): Runs great	$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB	Runs wellQwen3 14B verdict on the GeForce RTX 3060 12GB	est. 24.4 tok/s21.4–27.3calibrated estimate ±12%	Q4_K_M	11.1 / 12.0 GB	Full GPU	up to 8k	Q2_K (heavy quality loss): Runs great	$250 street (as of 2026-08-09)
GeForce GTX 1080 Ti	Runs well	est. 23.8 tok/s16.7–30.9theoretical estimate ±30%	Q4_K_M	11.0 / 11.0 GB + 0.5 GB RAM	Partial offload	up to 8k	Try IQ4_XS: Runs great	$699 launch MSRP
Radeon RX 9060 XT 16GB	Runs well	est. 23.7 tok/s20.8–26.5calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	Q2_K (heavy quality loss): Runs great	$449 street (as of 2026-08-09)
Apple M5 Pro · 24 GB	Runs well	est. 22.6 tok/s18.0–27.1calibrated estimate ±20%	Q4_K_M	10.9 / 16.8 GB	Unified memory	up to 32k	Q2_K (heavy quality loss): Runs great	—
NVIDIA DGX Spark · 128 GB	Runs well	est. 20.6 tok/s16.5–24.7calibrated estimate ±20%	Q4_K_M	10.9 / 116.9 GB	Unified memory	up to 32k	Q2_K (heavy quality loss): Runs great	$3,999 launch MSRP (128 GB)
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs well	est. 20.3 tok/s16.2–24.4calibrated estimate ±20%	Q4_K_M	10.9 / 22.4 GB	Unified memory	up to 32k	—	$1,999 launch MSRP (128 GB)
Apple M4 Pro · 24 GB	Runs wellQwen3 14B verdict on the Apple M4 Pro	est. 20.1 tok/s16.0–24.1calibrated estimate ±20%	Q4_K_M	10.9 / 16.8 GB	Unified memory	up to 32k	—	—
GeForce RTX 4060 Ti 16GB	Runs well	est. 19.5 tok/s17.2–21.8calibrated estimate ±12%	Q4_K_M	11.1 / 16.0 GB	Full GPU	up to 32k	—	$499 launch MSRP
Apple M6 · 24 GB	Runs well	est. 12.5 tok/s10.0–15.0calibrated estimate ±20%	Q4_K_M	10.9 / 16.8 GB	Unified memory	up to 8k	—	—
GeForce RTX 3080 10GB	Runs slowly	est. 18.2 tok/s14.5–21.8calibrated estimate ±20%	Q4_K_M	10.0 / 10.0 GB + 1.5 GB RAM	Partial offload	up to 32k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great	$699 launch MSRP
Apple M5 · 16 GB	Runs slowly	est. 11.3 tok/s9.0–13.5calibrated estimate ±20%	Q4_K_M	10.9 / 11.2 GB	Unified memory	up to 8k	Try IQ4_XS: Runs well	—
GeForce RTX 3070	Runs slowly	est. 9.1 tok/s7.3–10.9calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$499 launch MSRP
GeForce RTX 5060	Runs slowly	est. 9.1 tok/s7.3–10.9calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs slowly	est. 9.1 tok/s7.3–10.9calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$429 street (as of 2026-08-09)
Apple M4 · 16 GB	Runs slowlyQwen3 14B verdict on the Apple M4	est. 8.8 tok/s7.1–10.6calibrated estimate ±20%	Q4_K_M	10.9 / 11.2 GB	Unified memory	up to 8k	Q2_K (heavy quality loss): Runs well	—
GeForce RTX 4060 Ti 8GB	Runs slowly	est. 8.2 tok/s6.6–9.9calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$399 launch MSRP
GeForce RTX 4060	Runs slowlyQwen3 14B verdict on the GeForce RTX 4060	est. 8.1 tok/s6.5–9.7calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs slowly	est. 8.0 tok/s6.4–9.6calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	—
GeForce RTX 4070 Laptop	Runs slowly	est. 8.0 tok/s6.4–9.6calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	—
GeForce RTX 3050 8GB	Runs slowly	est. 7.7 tok/s6.1–9.2calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 3.5 GB RAM	Partial offload	up to 32k	Q2_K (heavy quality loss): Runs well	$249 launch MSRP
DDR5-6000 dual-channel CPU · 16 GB	Runs slowly	est. 4.6 tok/s3.7–5.6calibrated estimate ±20%	Q4_K_M	10.3 GB RAM	CPU only	up to 16k	—	—
DDR5-5600 dual-channel CPU · 16 GB	Runs slowly	est. 4.3 tok/s3.5–5.2calibrated estimate ±20%	Q4_K_M	10.3 GB RAM	CPU only	up to 16k	—	—
DDR4-3200 dual-channel CPU · 64 GB	Won't runTry Q2_K (heavy quality loss): Runs slowly	est. 3.6 tok/s2.9–4.3calibrated estimate ±20%	Q2_K	7.1 GB RAM	CPU only	up to 16k	—	—

Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.

Cheapest GPUs that run it

Runs greatGeForce RTX 5060 Ti 16GB$569 street (as of 2026-08-09), est. 30.3 tok/s (26.7–34.0, calibrated estimate ±12%).
Runs wellGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 24.4 tok/s (21.4–27.3, calibrated estimate ±12%).

Measured results for Qwen3 14B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Qwen3 14B need?

At Q4_K_M the file is 9.00 GB; with 8k context a graphics card needs about 10.5 GB (weights 8.56 GB, KV cache 1.3 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 7.4 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.

What is the cheapest GPU that runs Qwen3 14B well?

Cheapest that runs it great: GeForce RTX 5060 Ti 16GB at $569 (street price as of 2026-08-09), est. 30.3 tok/s (26.7–34.0, calibrated estimate ±12%). Cheaper and still Runs well: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 24.4 tok/s (21.4–27.3, calibrated estimate ±12%).

Can Qwen3 14B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs slowly, est. 8.1 tok/s (6.5–9.7, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs great, est. 30.3 tok/s (26.7–34.0, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 63.4 tok/s (55.7–71.0, calibrated estimate ±12%).

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.