v1.1.7

1.1.7 (2026-08-02)

Features

• cli: add provider filter to fit (#823) (bb5a341)
• detect RamaLama store models via ramalama ls when no server is running (#744) (850e809)
• tui: mark list rows matched through a GGUF source (#814) (ba1db79)
• tui: spell out active advanced range filters instead of cryptic R/M markers (8aee7ce)

Bug Fixes

• hardware: detect Jetson/Tegra Orin iGPU as unified memory (#792) (0e37d07)
• poll LM Studio's real download status endpoint (/api/v1/models/download/status/:job_id) and correct stale docs (f744292)
• send HF repo URLs to LM Studio downloads and parse single-object POST responses (b7fe566)

What's Changed

• feat(tui): spell out active advanced range filters instead of cryptic R/M markers by @AlexsJones in #783
• community: add NVIDIA GeForce RTX 5070 (40 models, llama.cpp) by @Akciali in #787
• bench: community results for nvidia-geforce-rtx-2070-super by @Goodgas00 in #788
• chore(deps): bump http from 1.4.1 to 1.4.2 by @dependabot[bot] in #767
• chore(deps): bump dorny/paths-filter from 4.0.1 to 4.0.2 by @dependabot[bot] in #736
• fix: poll LM Studio's real download status endpoint (/api/v1/models/download/status/:job_id) and correct stale docs by @mvanhorn in #728
• Move terminal clear before main loop by @benbaker76 in #786
• chore(deps): bump docker/login-action from 4.1.0 to 4.4.0 by @dependabot[bot] in #737
• chore(deps): bump peter-evans/create-pull-request from 7.0.11 to 8.1.1 by @dependabot[bot] in #738
• fix(hardware): detect Jetson/Tegra Orin iGPU as unified memory by @lucamaf in #792
• community: add AMD Radeon RX 7900 XT (40 models, llama.cpp Vulkan) by @Akciali in #808
• Add NVIDIA GeForce GTX 1050 Ti (4 GB, Vulkan) — 63 models by @Akciali in #815
• feat(tui): mark list rows matched through a GGUF source by @aramz33 in #814
• feat: detect RamaLama store models via ramalama ls when no server is running by @Olawoyin007 in #744
• feat(cli): add provider filter to fit by @SulimanAbdulrazzaq in #823
• community: add AMD Radeon RX 7900 XT, batch 2 (40 more models, llama.cpp Vulkan) by @Akciali in #821
• bench: community results for apple-m5-max by @DanzigerGeist in #822
• chore(main): release 1.1.7 by @AlexsJones in #784

New Contributors

• @Goodgas00 made their first contribution in #788
• @benbaker76 made their first contribution in #786
• @lucamaf made their first contribution in #792
• @SulimanAbdulrazzaq made their first contribution in #823
• @DanzigerGeist made their first contribution in #822

Full Changelog: v1.1.6...v1.1.7