Atlas3D
/

llama.cpp-sm70-cuda12.9

Model card Files Files and versions

llama.cpp-sm70-cuda12.9

46.7 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

orwelian84's picture

Add Tess-4.5-27B (dense) speed comparison beside MiniCPM

14b5896 verified about 19 hours ago

.gitattributes

1.52 kB
initial commit about 19 hours ago
LICENSE

1.08 kB
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
README.md

16.5 kB
Add Tess-4.5-27B (dense) speed comparison beside MiniCPM about 19 hours ago
RELEASE-NOTES.md

4.96 kB
Add Tess-4.5-27B (dense) speed comparison beside MiniCPM about 19 hours ago
REVALIDATION.json

15.7 kB
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
REVALIDATION.md

5.7 kB
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
SHA256SUMS

116 Bytes
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
THIRD-PARTY-NOTICES

11.3 kB
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
llama.cpp-f74e2fa-cuda12.9-sm70-linux-x64.tar.zst

46.6 MB
xet

llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
sm70-flash-attention.patch

417 Bytes
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago
source-local.patch

1.51 kB
llama.cpp f74e2fa for NVIDIA Volta (sm_70), CUDA 12.9 — released 2026-10-20 with the Q5_1 caveat stated about 19 hours ago