GPU NVIDIA GeForce RTX 4060 Ti, 16 GB
CPU 12th Gen Intel(R) Core(TM) i3-12100, 8 threads
RAM 63 GB DDR4 32G 2666 * 2
Model swift-1.5-iq3_xxs
Engine v0.1.43.1
Context 106,496 tokens
KV cache 8-bit, streamed: 20,480 positions per layer in VRAM, the rest in RAM
Experts in VRAM 5,038 (8.2 GB)
Speculation MTP drafts up to 3 tokens, prompt lookup on
Images on
