Models › Agnes-3.0-Qwen

Agnes-3.0-Qwen: VRAM needs and speed by GPU

At Q4_K_M, Agnes-3.0-Qwen needs about 130.1 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.

179.55B parameters · license: other · 1,048,576-token context · GGUF published Oct 20, 2026 · GGUF files on Hugging Face

Memory needed per quantization

QuantFile sizeNeeds (estimate)Smallest card it fits
IQ1_S73.9 GB76.9 GB96 GB cards
IQ1_M76.2 GB79.2 GB96 GB cards
IQ2_XS80.5 GB83.5 GB96 GB cards
IQ2_S82.3 GB85.3 GB96 GB cards
IQ2_M86.0 GB89.0 GB96 GB cards
Q2_K87.1 GB90.1 GB96 GB cards
Q3_K_S92.9 GB95.9 GBmulti-GPU / large unified memory
IQ3_XXS93.2 GB96.2 GBmulti-GPU / large unified memory
IQ3_XS95.4 GB98.4 GBmulti-GPU / large unified memory
Q3_K_M97.6 GB100.6 GBmulti-GPU / large unified memory
Q3_K_L101.2 GB104.2 GBmulti-GPU / large unified memory
IQ4_XS101.4 GB104.4 GBmulti-GPU / large unified memory
Q4_0102.1 GB105.1 GBmulti-GPU / large unified memory
IQ3_M102.5 GB105.5 GBmulti-GPU / large unified memory
IQ4_NL107.4 GB110.4 GBmulti-GPU / large unified memory
Q4_1112.7 GB115.7 GBmulti-GPU / large unified memory
Q4_K_S116.7 GB119.7 GBmulti-GPU / large unified memory
Q4_K_M127.1 GB130.1 GBmulti-GPU / large unified memory
Q5_K_S131.6 GB134.6 GBmulti-GPU / large unified memory
Q5_K_M142.6 GB145.6 GBmulti-GPU / large unified memory
Q6_K_S171.0 GB174.0 GBmulti-GPU / large unified memory
Q6_K174.5 GB177.5 GBmulti-GPU / large unified memory
Q8_0191.0 GB194.0 GBmulti-GPU / large unified memory
BF16359.2 GB362.2 GBmulti-GPU / large unified memory

Expected speed on popular hardware

HardwareBest quant that fitsExpected tok/s
NVIDIA RTX 3060Does not fit
NVIDIA RTX 4060 TiDoes not fit
NVIDIA RTX 3090Does not fit
NVIDIA RTX 4090Does not fit
NVIDIA RTX 5090Does not fit
AMD Radeon RX 7900 XTXDoes not fit
Apple M4 Pro (20-core GPU)Does not fit
Apple M3 Max (40-core GPU)Does not fit
AMD Ryzen AI Max+ 395 (Radeon 8060S)Q3_K_S2.2 estimate

Check your own card

Too big for your card?

Run Agnes-3.0-Qwen 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.