https://gpufit.tech/gpu/tesla-t4/New catalog models scored against NVIDIA T4.https://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4b/https://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4b/Fri, 23 Oct 2026 09:47:55 GMTTight fit fully on your NVIDIA T4 at BF16, 8K context, about 11–15 tok/s. Weights 14.0 GB plus 0.14 GB of KV cache — 14.6 GB of 15.2 GB usable. Up to 16K context still fits. 11–15 tok/s.https://gpufit.tech/models/deepseek-v4-1-flash-1017/https://gpufit.tech/models/deepseek-v4-1-flash-1017/Sat, 17 Oct 2026 20:36:06 GMTWon't fit on NVIDIA T4. The smallest quant UD-IQ1_S is 217.0 GB before KV cache, and usable memory is 15.2 GB.https://gpufit.tech/models/lfm2-5-24b-a2b/https://gpufit.tech/models/lfm2-5-24b-a2b/Tue, 13 Oct 2026 14:19:48 GMTTight fit fully on your NVIDIA T4 at UD-Q4_K_XL, 4K context, about 28–38 tok/s. Weights 13.9 GB plus 0.31 GB of KV cache — 14.6 GB of 15.2 GB usable. 28–38 tok/s.