What runs on your GPU

Pick your GPU's memory. Open models in their original precision, no quantization: which fit on one card in bf16, which fit only with Glyd, and how much room is left for the context.

16 GBRTX 4080, 4080 SUPER, 5080, 5070 Ti and 4060 Ti 16 GB3 only with Glyd · 3 either wayWhat runs on it
24 GBRTX 4090, RTX 3090 and A103 only with Glyd · 6 either wayWhat runs on it
32 GBRTX 50900 only with Glyd · 9 either wayWhat runs on it
48 GBRTX A6000, L40S and RTX 6000 Ada6 only with Glyd · 10 either wayWhat runs on it
80 GBH100 and A100 80 GB0 only with Glyd · 16 either wayWhat runs on it
96 GBRTX PRO 6000 and GH2002 only with Glyd · 16 either wayWhat runs on it
141 GBH2002 only with Glyd · 18 either wayWhat runs on it

Updated Sep 27, 2026. A model fits when its weights, an 8K-token KV cache and 1.5 GB for the runtime fit in the memory nvidia-smi reports. Sizes measured where marked; est. means worked out from the parameter count, run queued.