Models › Qwen3-14B

Qwen3-14B: VRAM needs and speed by GPU

At Q4_K_M, Qwen3-14B needs about 10.2 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.

14.77B parameters · license: apache-2.0 · 40,960-token context · GGUF published Apr 28, 2025 · GGUF files on Hugging Face

Memory needed per quantization

QuantFile sizeNeeds (estimate)Smallest card it fits
UD-IQ1_S3.8 GB5.0 GB8 GB cards
UD-IQ1_M4.1 GB5.2 GB8 GB cards
UD-IQ2_XXS4.5 GB5.6 GB8 GB cards
UD-IQ2_M5.4 GB6.6 GB8 GB cards
Q2_K5.8 GB6.9 GB8 GB cards
Q2_K_L5.9 GB7.1 GB8 GB cards
UD-IQ3_XXS6.0 GB7.2 GB8 GB cards
UD-Q2_K_XL6.1 GB7.2 GB8 GB cards
Q3_K_S6.7 GB7.8 GB12 GB cards
Q3_K_M7.3 GB8.5 GB12 GB cards
UD-Q3_K_XL7.6 GB8.8 GB12 GB cards
IQ4_XS8.1 GB9.3 GB12 GB cards
IQ4_NL8.5 GB9.7 GB12 GB cards
Q4_08.5 GB9.7 GB12 GB cards
Q4_K_S8.6 GB9.7 GB12 GB cards
Q4_K_M9.0 GB10.2 GB12 GB cards
UD-Q4_K_XL9.2 GB10.3 GB12 GB cards
Q4_19.4 GB10.6 GB12 GB cards
Q5_K_S10.3 GB11.4 GB12 GB cards
Q5_K_M10.5 GB11.7 GB16 GB cards
UD-Q5_K_XL10.5 GB11.7 GB16 GB cards
Q6_K12.1 GB13.3 GB16 GB cards
UD-Q6_K_XL13.3 GB14.5 GB16 GB cards
Q8_015.7 GB16.9 GB24 GB cards
UD-Q8_K_XL18.8 GB19.9 GB24 GB cards
BF1629.5 GB30.7 GB32 GB cards

Expected speed on popular hardware

HardwareBest quant that fitsExpected tok/s
NVIDIA RTX 3060Q5_K_S30.0 estimate
NVIDIA RTX 4060 TiUD-IQ3_XXS40.7 estimate
NVIDIA RTX 3090Q8_041.8 estimate
NVIDIA RTX 4090Q8_046.3 estimate
NVIDIA RTX 5090Q8_073.1 estimate
AMD Radeon RX 7900 XTXQ8_046.5 estimate
Apple M4 Pro (20-core GPU) (64 GB)Q8_014.7 estimate
Apple M3 Max (40-core GPU) (64 GB)Q8_021.5 estimate
AMD Ryzen AI Max+ 395 (Radeon 8060S)Q8_013.2 estimate

Check your own card

Too big for your card?

Run Qwen3-14B on a rented 24-80 GB GPU by the hour.

Rent a bigger GPU on RunPod

Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.