-
Updated
Jan 3, 2026 - Python
sm61
Here are 7 public repositories matching this topic...
Ternary Bonsai 2 9B on a GTX 1080 (sm_61): +51% decode with bit-identical output (PrismML llama.cpp fork, PQ2_0 + MTP)
-
Updated
Nov 16, 2026 - Python
llama.cpp CUDA DP4A/MMQ tuning for NVIDIA Pascal (SM 6.1), Tesla P40 and GTX 10. / Патчи llama.cpp для Pascal и Tesla P40.
-
Updated
Nov 18, 2026 - Shell
MiniCPM5-2B on a GTX 1080 (Pascal, sm_61): from 33 to 83 tokens/s with llama.cpp kernels, KV f16 and an FR-Spec draft, bit-identical where it matters
-
Updated
Oct 24, 2026 - Python
Everything I made run fast on a 2016 GPU with 8 GB: llama.cpp kernels, CUDA graphs, speculative decoding, ternary models, LoRA training, video diffusion on a GTX 1080 (sm_61). Measured, with sources.
-
Updated
Nov 3, 2026 - Python
AR → discrete diffusion LLM backend (LLaDA 2.1 recipe, Qwen3-0.6B, Pascal/sm_61)
-
Updated
Oct 2, 2026 - Python
Add this topic to your repo
To associate your repository with the sm61 topic, visit your repo's landing page and select "manage topics."